📃Papers | X

2024

Advanced Long-Content Speech Recognition With Factorized Neural Transducer

Xun Gong , Yu Wu , Jinyu Li , Shujie Liu , Rui Zhao , Xie Chen, and Yanmin Qian

IEEE ACM Trans. Audio Speech Lang. Process., 2024

@article{Gong2024,
  author = {Gong, Xun and Wu, Yu and Li, Jinyu and Liu, Shujie and Zhao, Rui and Chen, Xie and Qian, Yanmin},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Advanced Long-Content Speech Recognition With Factorized Neural Transducer},
  year = {2024},
  pages = {1803--1815},
  volume = {32},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/GongWLLZCQ24.bib},
  doi = {10.1109/TASLP.2024.3350893},
  timestamp = {Thu, 21 Mar 2024 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2024.3350893}
}

EAT: Self-Supervised Pre-Training with Efficient Audio Transformer

Wenxi Chen , Yuzhe Liang , Ziyang Ma , Zhisheng Zheng , and Xie Chen

CoRR, 2024

Bib

@article{Chen2024,
  author = {Chen, Wenxi and Liang, Yuzhe and Ma, Ziyang and Zheng, Zhisheng and Chen, Xie},
  journal = {CoRR},
  title = {{EAT:} Self-Supervised Pre-Training with Efficient Audio Transformer},
  year = {2024},
  volume = {abs/2401.03497},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2401-03497.bib},
  doi = {10.48550/ARXIV.2401.03497},
  eprint = {2401.03497},
  timestamp = {Fri, 26 Jan 2024 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2401.03497}
}

ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering

Yakun Song , Zhuo Chen , Xiaofei Wang , Ziyang Ma , and Xie Chen

CoRR, 2024

Bib

@article{Song2024,
  author = {Song, Yakun and Chen, Zhuo and Wang, Xiaofei and Ma, Ziyang and Chen, Xie},
  journal = {CoRR},
  title = {{ELLA-V:} Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering},
  year = {2024},
  volume = {abs/2401.07333},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2401-07333.bib},
  doi = {10.48550/ARXIV.2401.07333},
  eprint = {2401.07333},
  timestamp = {Thu, 01 Feb 2024 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2401.07333}
}

BAT: Learning to Reason about Spatial Sounds with Large Language Models

Zhisheng Zheng , Puyuan Peng , Ziyang Ma , Xie Chen, Eunsol Choi , and David Harwath

CoRR, 2024

Bib

@article{Zheng2024,
  author = {Zheng, Zhisheng and Peng, Puyuan and Ma, Ziyang and Chen, Xie and Choi, Eunsol and Harwath, David},
  journal = {CoRR},
  title = {{BAT:} Learning to Reason about Spatial Sounds with Large Language Models},
  year = {2024},
  volume = {abs/2402.01591},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2402-01591.bib},
  doi = {10.48550/ARXIV.2402.01591},
  eprint = {2402.01591},
  timestamp = {Wed, 14 Feb 2024 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2402.01591}
}

An Embarrassingly Simple Approach for LLM with Strong ASR Capacity

Ziyang Ma , Guanrou Yang , Yifan Yang , Zhifu Gao , Jiaming Wang , Zhihao Du , Fan Yu , Qian Chen , Siqi Zheng , Shiliang Zhang , and Xie Chen

CoRR, 2024

Bib

@article{Ma2024,
  author = {Ma, Ziyang and Yang, Guanrou and Yang, Yifan and Gao, Zhifu and Wang, Jiaming and Du, Zhihao and Yu, Fan and Chen, Qian and Zheng, Siqi and Zhang, Shiliang and Chen, Xie},
  journal = {CoRR},
  title = {An Embarrassingly Simple Approach for {LLM} with Strong {ASR} Capacity},
  year = {2024},
  volume = {abs/2402.08846},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2402-08846.bib},
  doi = {10.48550/ARXIV.2402.08846},
  eprint = {2402.08846},
  timestamp = {Mon, 19 Feb 2024 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2402.08846}
}

Beyond the Status Quo: A Contemporary Survey of Advances and Challenges in Audio Captioning

Xuenan Xu , Zeyu Xie , Mengyue Wu, and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., 2024

Bib

@article{Xu2024,
  author = {Xu, Xuenan and Xie, Zeyu and Wu, Mengyue and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Beyond the Status Quo: {A} Contemporary Survey of Advances and Challenges in Audio Captioning},
  year = {2024},
  pages = {95--112},
  volume = {32},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/XuXWY24.bib},
  doi = {10.1109/TASLP.2023.3321968},
  timestamp = {Thu, 09 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2023.3321968}
}

Towards Weakly Supervised Text-to-Audio Grounding

Xuenan Xu , Ziyang Ma , Mengyue Wu, and Kai Yu

CoRR, 2024

Bib

@article{Xu2024a,
  author = {Xu, Xuenan and Ma, Ziyang and Wu, Mengyue and Yu, Kai},
  journal = {CoRR},
  title = {Towards Weakly Supervised Text-to-Audio Grounding},
  year = {2024},
  volume = {abs/2401.02584},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2401-02584.bib},
  doi = {10.48550/ARXIV.2401.02584},
  eprint = {2401.02584},
  timestamp = {Tue, 23 Jan 2024 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2401.02584}
}

VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech

Chenpeng Du , Yiwei Guo , Hankun Wang , Yifan Yang , Zhikang Niu , Shuai Wang , Hui Zhang , Xie Chen, and Kai Yu

CoRR, 2024

Bib

@article{Du2024,
  author = {Du, Chenpeng and Guo, Yiwei and Wang, Hankun and Yang, Yifan and Niu, Zhikang and Wang, Shuai and Zhang, Hui and Chen, Xie and Yu, Kai},
  journal = {CoRR},
  title = {{VALL-T:} Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech},
  year = {2024},
  volume = {abs/2401.14321},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2401-14321.bib},
  doi = {10.48550/ARXIV.2401.14321},
  eprint = {2401.14321},
  timestamp = {Wed, 07 Feb 2024 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2401.14321}
}

ChemDFM: Dialogue Foundation Model for Chemistry

Zihan Zhao , Da Ma , Lu Chen, Liangtai Sun , Zihao Li , Hongshen Xu , Zichen Zhu , Su Zhu , Shuai Fan , Guodong Shen , Xin Chen , and Kai Yu

CoRR, 2024

Bib

@article{Zhao2024,
  author = {Zhao, Zihan and Ma, Da and Chen, Lu and Sun, Liangtai and Li, Zihao and Xu, Hongshen and Zhu, Zichen and Zhu, Su and Fan, Shuai and Shen, Guodong and Chen, Xin and Yu, Kai},
  journal = {CoRR},
  title = {ChemDFM: Dialogue Foundation Model for Chemistry},
  year = {2024},
  volume = {abs/2401.14818},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2401-14818.bib},
  doi = {10.48550/ARXIV.2401.14818},
  eprint = {2401.14818},
  timestamp = {Tue, 06 Feb 2024 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2401.14818}
}

MULTI: Multimodal Understanding Leaderboard with Text and Images

Zichen Zhu, Yang Xu , Lu Chen, Jingkai Yang , Yichuan Ma , Yiming Sun , Hailin Wen , Jiaqi Liu , Jinyu Cai , Yingzi Ma , Situo Zhang , Zihan Zhao , Liangtai Sun , and Kai Yu

CoRR, 2024

Bib

@article{Zhu2024,
  author = {Zhu, Zichen and Xu, Yang and Chen, Lu and Yang, Jingkai and Ma, Yichuan and Sun, Yiming and Wen, Hailin and Liu, Jiaqi and Cai, Jinyu and Ma, Yingzi and Zhang, Situo and Zhao, Zihan and Sun, Liangtai and Yu, Kai},
  journal = {CoRR},
  title = {{MULTI:} Multimodal Understanding Leaderboard with Text and Images},
  year = {2024},
  volume = {abs/2402.03173},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2402-03173.bib},
  doi = {10.48550/ARXIV.2402.03173},
  eprint = {2402.03173},
  timestamp = {Mon, 26 Feb 2024 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2402.03173}
}

2023

A Unified Framework From Face Image Restoration to Data Augmentation Using Generative Prior

Jiawei You , Ganyu Huang , Tianyuan Han , Haoze Yang , and Liping Shen

IEEE Access, 2023

Bib

@article{You2023,
  author = {You, Jiawei and Huang, Ganyu and Han, Tianyuan and Yang, Haoze and Shen, Liping},
  journal = {{IEEE} Access},
  title = {A Unified Framework From Face Image Restoration to Data Augmentation Using Generative Prior},
  year = {2023},
  pages = {2907--2919},
  volume = {11},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/access/YouHHYS23.bib},
  doi = {10.1109/ACCESS.2022.3233868},
  timestamp = {Tue, 31 Jan 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ACCESS.2022.3233868}
}

Human Pose Estimation with Combined Feature Maps and Joint Embeddings

Tianyuan Han , Ganyu Huang , Chunhui Li , and Liping Shen

In Proceedings of the 2023 International Conference on Advances in Artificial Intelligence and Applications, AAIA 2023, Wuhan, China, November 18-20, 2023 , 2023

Bib

@inproceedings{Han2023,
  author = {Han, Tianyuan and Huang, Ganyu and Li, Chunhui and Shen, Liping},
  booktitle = {Proceedings of the 2023 International Conference on Advances in Artificial Intelligence and Applications, {AAIA} 2023, Wuhan, China, November 18-20, 2023},
  title = {Human Pose Estimation with Combined Feature Maps and Joint Embeddings},
  year = {2023},
  pages = {101--106},
  publisher = {{ACM}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/aaia/HanHLS23.bib},
  doi = {10.1145/3603273.3636495},
  timestamp = {Sat, 13 Jan 2024 00:00:00 +0100},
  url = {https://doi.org/10.1145/3603273.3636495}
}

Assessing and Enhancing LLMs: A Physics and History Dataset and One-More-Check Pipeline Method

Chaofan He , Chunhui Li , Tianyuan Han , and Liping Shen

In Neural Information Processing - 30th International Conference, ICONIP 2023, Changsha, China, November 20-23, 2023, Proceedings, Part XIII , 2023

Bib

@inproceedings{He2023,
  author = {He, Chaofan and Li, Chunhui and Han, Tianyuan and Shen, Liping},
  booktitle = {Neural Information Processing - 30th International Conference, {ICONIP} 2023, Changsha, China, November 20-23, 2023, Proceedings, Part {XIII}},
  title = {Assessing and Enhancing LLMs: {A} Physics and History Dataset and One-More-Check Pipeline Method},
  year = {2023},
  editor = {Luo, Biao and Cheng, Long and Wu, Zheng{-}Guang and Li, Hongyi and Li, Chaojie},
  pages = {504--517},
  publisher = {Springer},
  series = {Communications in Computer and Information Science},
  volume = {1967},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iconip/HeLHS23.bib},
  doi = {10.1007/978-981-99-8178-6\_38},
  timestamp = {Mon, 18 Dec 2023 09:47:49 +0100},
  url = {https://doi.org/10.1007/978-981-99-8178-6\_38}
}

GAN Latent Space Manipulation Based Augmentation for Unbalanced Emotion Datasets

Yuhan Xiong , Jiawei You , and Liping Shen

In International Joint Conference on Neural Networks, IJCNN 2023, Gold Coast, Australia, June 18-23, 2023 , 2023

Bib

@inproceedings{Xiong2023,
  author = {Xiong, Yuhan and You, Jiawei and Shen, Liping},
  booktitle = {International Joint Conference on Neural Networks, {IJCNN} 2023, Gold Coast, Australia, June 18-23, 2023},
  title = {{GAN} Latent Space Manipulation Based Augmentation for Unbalanced Emotion Datasets},
  year = {2023},
  pages = {1--8},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/ijcnn/XiongYS23.bib},
  doi = {10.1109/IJCNN54540.2023.10191807},
  timestamp = {Wed, 09 Aug 2023 16:25:09 +0200},
  url = {https://doi.org/10.1109/IJCNN54540.2023.10191807}
}

LongFNT: Long-Form Speech Recognition with Factorized Neural Transducer

Xun Gong , Yu Wu , Jinyu Li , Shujie Liu , Rui Zhao , Xie Chen, and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , 2023

Bib

@inproceedings{Gong2023,
  author = {Gong, Xun and Wu, Yu and Li, Jinyu and Liu, Shujie and Zhao, Rui and Chen, Xie and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {LongFNT: Long-Form Speech Recognition with Factorized Neural Transducer},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/GongWLLZCQ23.bib},
  doi = {10.1109/ICASSP49357.2023.10096900},
  timestamp = {Sun, 05 Nov 2023 16:51:21 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10096900}
}

Factorized AED: Factorized Attention-Based Encoder-Decoder for Text-Only Domain Adaptive ASR

Xun Gong , Wei Wang , Hang Shao , Xie Chen, and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , 2023

Bib

@inproceedings{Gong2023a,
  author = {Gong, Xun and Wang, Wei and Shao, Hang and Chen, Xie and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {Factorized {AED:} Factorized Attention-Based Encoder-Decoder for Text-Only Domain Adaptive {ASR}},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/GongWSCQ23.bib},
  doi = {10.1109/ICASSP49357.2023.10095937},
  timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10095937}
}

Exploring Binary Classification Loss for Speaker Verification

Bing Han , Zhengyang Chen , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , 2023

Bib

@inproceedings{Han2023a,
  author = {Han, Bing and Chen, Zhengyang and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {Exploring Binary Classification Loss for Speaker Verification},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/HanCQ23.bib},
  doi = {10.1109/ICASSP49357.2023.10094954},
  timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10094954}
}

Improving Dino-Based Self-Supervised Speaker Verification with Progressive Cluster-Aware Training

Bing Han , Wen Huang , Zhengyang Chen , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2023 - Workshops, Rhodes Island, Greece, June 4-10, 2023 , 2023

Bib

@inproceedings{Han2023b,
  author = {Han, Bing and Huang, Wen and Chen, Zhengyang and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2023 - Workshops, Rhodes Island, Greece, June 4-10, 2023},
  title = {Improving Dino-Based Self-Supervised Speaker Verification with Progressive Cluster-Aware Training},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/HanHCQ23.bib},
  doi = {10.1109/ICASSPW59220.2023.10192957},
  timestamp = {Mon, 07 Aug 2023 15:56:26 +0200},
  url = {https://doi.org/10.1109/ICASSPW59220.2023.10192957}
}

Robust Audio-Visual ASR with Unified Cross-Modal Attention

Jiahong Li , Chenda Li , Yifei Wu , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , 2023

Bib

@inproceedings{Li2023,
  author = {Li, Jiahong and Li, Chenda and Wu, Yifei and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {Robust Audio-Visual {ASR} with Unified Cross-Modal Attention},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/LiLWQ23.bib},
  doi = {10.1109/ICASSP49357.2023.10096893},
  timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10096893}
}

Target Sound Extraction with Variable Cross-Modality Clues

Chenda Li , Yao Qian , Zhuo Chen , Dongmei Wang , Takuya Yoshioka , Shujie Liu , Yanmin Qian , and Michael Zeng

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , 2023

Bib

@inproceedings{Li2023a,
  author = {Li, Chenda and Qian, Yao and Chen, Zhuo and Wang, Dongmei and Yoshioka, Takuya and Liu, Shujie and Qian, Yanmin and Zeng, Michael},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {Target Sound Extraction with Variable Cross-Modality Clues},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/LiQCWYLQZ23.bib},
  doi = {10.1109/ICASSP49357.2023.10095266},
  timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10095266}
}

Predictive Skim: Contrastive Predictive Coding for Low-Latency Online Speech Separation

Chenda Li , Yifei Wu , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , 2023

Bib

@inproceedings{Li2023b,
  author = {Li, Chenda and Wu, Yifei and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {Predictive Skim: Contrastive Predictive Coding for Low-Latency Online Speech Separation},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/LiWQ23.bib},
  doi = {10.1109/ICASSP49357.2023.10097107},
  timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10097107}
}

Multi-Speaker End-to-End Multi-Modal Speaker Diarization System for the MISP 2022 Challenge

Tao Liu , Zhengyang Chen , Yanmin Qian , and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , 2023

Bib

@inproceedings{Liu2023,
  author = {Liu, Tao and Chen, Zhengyang and Qian, Yanmin and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {Multi-Speaker End-to-End Multi-Modal Speaker Diarization System for the {MISP} 2022 Challenge},
  year = {2023},
  pages = {1--2},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/LiuCQY23.bib},
  doi = {10.1109/ICASSP49357.2023.10096327},
  timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10096327}
}

Joint Discriminator and Transfer Based Fast Domain Adaptation For End-To-End Speech Recognition

Hang Shao , Tian Tan , Wei Wang , Xun Gong , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , 2023

Bib

@inproceedings{Shao2023,
  author = {Shao, Hang and Tan, Tian and Wang, Wei and Gong, Xun and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {Joint Discriminator and Transfer Based Fast Domain Adaptation For End-To-End Speech Recognition},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ShaoTWGQ23.bib},
  doi = {10.1109/ICASSP49357.2023.10095910},
  timestamp = {Mon, 20 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10095910}
}

Lowbit Neural Network Quantization for Speaker Verification

Haoyu Wang , Bei Liu , Yifei Wu , Zhengyang Chen , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2023 - Workshops, Rhodes Island, Greece, June 4-10, 2023 , 2023

Bib

@inproceedings{Wang2023,
  author = {Wang, Haoyu and Liu, Bei and Wu, Yifei and Chen, Zhengyang and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2023 - Workshops, Rhodes Island, Greece, June 4-10, 2023},
  title = {Lowbit Neural Network Quantization for Speaker Verification},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/WangLWCQ23.bib},
  doi = {10.1109/ICASSPW59220.2023.10193337},
  timestamp = {Mon, 07 Aug 2023 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSPW59220.2023.10193337}
}

Wespeaker: A Research and Production Oriented Speaker Embedding Learning Toolkit

Hongji Wang , Chengdong Liang , Shuai Wang , Zhengyang Chen , Binbin Zhang , Xu Xiang , Yanlei Deng , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , 2023

Bib

@inproceedings{Wang2023a,
  author = {Wang, Hongji and Liang, Chengdong and Wang, Shuai and Chen, Zhengyang and Zhang, Binbin and Xiang, Xu and Deng, Yanlei and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {Wespeaker: {A} Research and Production Oriented Speaker Embedding Learning Toolkit},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/WangLWCZXDQ23.bib},
  doi = {10.1109/ICASSP49357.2023.10096626},
  timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10096626}
}

HuBERT-AGG: Aggregated Representation Distillation of Hidden-Unit Bert for Robust Speech Recognition

Wei Wang , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , 2023

Bib

@inproceedings{Wang2023b,
  author = {Wang, Wei and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {HuBERT-AGG: Aggregated Representation Distillation of Hidden-Unit Bert for Robust Speech Recognition},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/WangQ23.bib},
  doi = {10.1109/ICASSP49357.2023.10096308},
  timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10096308}
}

Light-Weight Visualvoice: Neural Network Quantization On Audio Visual Speech Separation

Yifei Wu , Chenda Li , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2023 - Workshops, Rhodes Island, Greece, June 4-10, 2023 , 2023

Bib

@inproceedings{Wu2023,
  author = {Wu, Yifei and Li, Chenda and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2023 - Workshops, Rhodes Island, Greece, June 4-10, 2023},
  title = {Light-Weight Visualvoice: Neural Network Quantization On Audio Visual Speech Separation},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/WuLQ23.bib},
  doi = {10.1109/ICASSPW59220.2023.10193263},
  timestamp = {Mon, 07 Aug 2023 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSPW59220.2023.10193263}
}

Code-Switching Text Generation and Injection in Mandarin-English ASR

Haibin Yu , Yuxuan Hu , Yao Qian , Ma Jin , Linquan Liu , Shujie Liu , Yu Shi , Yanmin Qian , Edward Lin , and Michael Zeng

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , 2023

Bib

@inproceedings{Yu2023,
  author = {Yu, Haibin and Hu, Yuxuan and Qian, Yao and Jin, Ma and Liu, Linquan and Liu, Shujie and Shi, Yu and Qian, Yanmin and Lin, Edward and Zeng, Michael},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {Code-Switching Text Generation and Injection in Mandarin-English {ASR}},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/YuHQJLLSQLZ23.bib},
  doi = {10.1109/ICASSP49357.2023.10096317},
  timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10096317}
}

Adaptive Large Margin Fine-Tuning For Robust Speaker Verification

Leying Zhang , Zhengyang Chen , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , 2023

Bib

@inproceedings{Zhang2023,
  author = {Zhang, Leying and Chen, Zhengyang and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {Adaptive Large Margin Fine-Tuning For Robust Speaker Verification},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ZhangCQ23.bib},
  doi = {10.1109/ICASSP49357.2023.10094744},
  timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10094744}
}

ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation

Chenyang Le , Yao Qian , Long Zhou , Shujie Liu , Yanmin Qian , Michael Zeng , and Xuedong Huang

In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023 , 2023

Bib

@inproceedings{Le2023,
  author = {Le, Chenyang and Qian, Yao and Zhou, Long and Liu, Shujie and Qian, Yanmin and Zeng, Michael and Huang, Xuedong},
  booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
  title = {ComSL: {A} Composite Speech-Language Model for End-to-End Speech-to-Text Translation},
  year = {2023},
  editor = {Oh, Alice and Naumann, Tristan and Globerson, Amir and Saenko, Kate and Hardt, Moritz and Levine, Sergey},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/nips/LeQZLQ0023.bib},
  timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
  url = {http://papers.nips.cc/paper\_files/paper/2023/hash/b6262f7a34e5d641cdb3d33dc9ad1a5a-Abstract-Conference.html}
}

Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation

Yoshiki Masuyama , Xuankai Chang , Wangyou Zhang , Samuele Cornell , Zhong-Qiu Wang , Nobutaka Ono , Yanmin Qian , and Shinji Watanabe

In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2023, New Paltz, NY, USA, October 22-25, 2023 , 2023

Bib

@inproceedings{Masuyama2023,
  author = {Masuyama, Yoshiki and Chang, Xuankai and Zhang, Wangyou and Cornell, Samuele and Wang, Zhong{-}Qiu and Ono, Nobutaka and Qian, Yanmin and Watanabe, Shinji},
  booktitle = {{IEEE} Workshop on Applications of Signal Processing to Audio and Acoustics, {WASPAA} 2023, New Paltz, NY, USA, October 22-25, 2023},
  title = {Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/waspaa/MasuyamaCZCWOQW23.bib},
  doi = {10.1109/WASPAA58266.2023.10248096},
  timestamp = {Sat, 23 Sep 2023 11:31:10 +0200},
  url = {https://doi.org/10.1109/WASPAA58266.2023.10248096}
}

Software Design and User Interface of ESPnet-SE++: Speech Enhancement for Robust Speech Processing (espnet-v.202310) (Version 1)

Yen-Ju Lu , Xuankai Chang , Chenda Li , Wangyou Zhang , Samuele Cornell , Zhaoheng Ni , Yoshiki Masuyama , Brian Yan , Robin Scheibler , Zhong-Qiu Wang , Yu Tsao , Yanmin Qian , and Shinji Watanabe

Oct 2023

Accessed on YYYY-MM-DD.

Bib

@misc{Lu2023,
  author = {Lu, Yen{-}Ju and Chang, Xuankai and Li, Chenda and Zhang, Wangyou and Cornell, Samuele and Ni, Zhaoheng and Masuyama, Yoshiki and Yan, Brian and Scheibler, Robin and Wang, Zhong{-}Qiu and Tsao, Yu and Qian, Yanmin and Watanabe, Shinji},
  howpublished = {\url{https://doi.org/10.5281/zenodo.10048174}},
  month = oct,
  note = {Accessed on YYYY-MM-DD.},
  title = {Software Design and User Interface of ESPnet-SE++: Speech Enhancement for Robust Speech Processing (espnet-v.202310) (Version 1)},
  year = {2023},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/data/10/LuCLZCNMYSWTQW23.bib},
  doi = {10.5281/ZENODO.10048174},
  publisher = {Zenodo},
  timestamp = {Tue, 21 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.5281/zenodo.10048174}
}

Self-Supervised Learning with Cluster-Aware-DINO for High-Performance Robust Speaker Verification

Bing Han , Zhengyang Chen , and Yanmin Qian

CoRR, Oct 2023

Bib

@article{Han2023c,
  author = {Han, Bing and Chen, Zhengyang and Qian, Yanmin},
  journal = {CoRR},
  title = {Self-Supervised Learning with Cluster-Aware-DINO for High-Performance Robust Speaker Verification},
  year = {2023},
  volume = {abs/2304.05754},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2304-05754.bib},
  doi = {10.48550/ARXIV.2304.05754},
  eprint = {2304.05754},
  timestamp = {Wed, 19 Apr 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2304.05754}
}

Attention-based Encoder-Decoder Network for End-to-End Neural Speaker Diarization with Target Speaker Attractor

Zhengyang Chen , Bing Han , Shuai Wang , and Yanmin Qian

CoRR, Oct 2023

Bib

@article{Chen2023,
  author = {Chen, Zhengyang and Han, Bing and Wang, Shuai and Qian, Yanmin},
  journal = {CoRR},
  title = {Attention-based Encoder-Decoder Network for End-to-End Neural Speaker Diarization with Target Speaker Attractor},
  year = {2023},
  volume = {abs/2305.10704},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2305-10704.bib},
  doi = {10.48550/ARXIV.2305.10704},
  eprint = {2305.10704},
  timestamp = {Thu, 25 May 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2305.10704}
}

Whisper-KDQ: A Lightweight Whisper via Guided Knowledge Distillation and Quantization for Efficient ASR

Hang Shao , Wei Wang , Bei Liu , Xun Gong , Haoyu Wang , and Yanmin Qian

CoRR, Oct 2023

Bib

@article{Shao2023a,
  author = {Shao, Hang and Wang, Wei and Liu, Bei and Gong, Xun and Wang, Haoyu and Qian, Yanmin},
  journal = {CoRR},
  title = {Whisper-KDQ: {A} Lightweight Whisper via Guided Knowledge Distillation and Quantization for Efficient {ASR}},
  year = {2023},
  volume = {abs/2305.10788},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2305-10788.bib},
  doi = {10.48550/ARXIV.2305.10788},
  eprint = {2305.10788},
  timestamp = {Thu, 25 May 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2305.10788}
}

Weakly-Supervised Speech Pre-training: A Case Study on Target Speech Recognition

Wangyou Zhang , and Yanmin Qian

CoRR, Oct 2023

Bib

@article{Zhang2023a,
  author = {Zhang, Wangyou and Qian, Yanmin},
  journal = {CoRR},
  title = {Weakly-Supervised Speech Pre-training: {A} Case Study on Target Speech Recognition},
  year = {2023},
  volume = {abs/2305.16286},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2305-16286.bib},
  doi = {10.48550/ARXIV.2305.16286},
  eprint = {2305.16286},
  timestamp = {Tue, 06 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2305.16286}
}

Adapting Multi-Lingual ASR Models for Handling Multiple Talkers

Chenda Li , Yao Qian , Zhuo Chen , Naoyuki Kanda , Dongmei Wang , Takuya Yoshioka , Yanmin Qian , and Michael Zeng

CoRR, Oct 2023

Bib

@article{Li2023d,
  author = {Li, Chenda and Qian, Yao and Chen, Zhuo and Kanda, Naoyuki and Wang, Dongmei and Yoshioka, Takuya and Qian, Yanmin and Zeng, Michael},
  journal = {CoRR},
  title = {Adapting Multi-Lingual {ASR} Models for Handling Multiple Talkers},
  year = {2023},
  volume = {abs/2305.18747},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2305-18747.bib},
  doi = {10.48550/ARXIV.2305.18747},
  eprint = {2305.18747},
  timestamp = {Sat, 04 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2305.18747}
}

InstructME: An Instruction Guided Music Edit And Remix Framework with Latent Diffusion Models

Bing Han , Junyu Dai , Xuchen Song , Weituo Hao , Xinyan He , Dong Guo , Jitong Chen , Yuxuan Wang , and Yanmin Qian

CoRR, Oct 2023

Bib

@article{Han2023e,
  author = {Han, Bing and Dai, Junyu and Song, Xuchen and Hao, Weituo and He, Xinyan and Guo, Dong and Chen, Jitong and Wang, Yuxuan and Qian, Yanmin},
  journal = {CoRR},
  title = {InstructME: An Instruction Guided Music Edit And Remix Framework with Latent Diffusion Models},
  year = {2023},
  volume = {abs/2308.14360},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2308-14360.bib},
  doi = {10.48550/ARXIV.2308.14360},
  eprint = {2308.14360},
  timestamp = {Fri, 01 Sep 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2308.14360}
}

Attention-based Encoder-Decoder End-to-End Neural Diarization with Embedding Enhancer

Zhengyang Chen , Bing Han , Shuai Wang , and Yanmin Qian

CoRR, Oct 2023

Bib

@article{Chen2023a,
  author = {Chen, Zhengyang and Han, Bing and Wang, Shuai and Qian, Yanmin},
  journal = {CoRR},
  title = {Attention-based Encoder-Decoder End-to-End Neural Diarization with Embedding Enhancer},
  year = {2023},
  volume = {abs/2309.06672},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2309-06672.bib},
  doi = {10.48550/ARXIV.2309.06672},
  eprint = {2309.06672},
  timestamp = {Tue, 19 Sep 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2309.06672}
}

USED: Universal Speaker Extraction and Diarization

Junyi Ao , Mehmet Sinan Yildirim , Meng Ge , Shuai Wang , Ruijie Tao , Yanmin Qian , Liqun Deng , Longshuai Xiao , and Haizhou Li

CoRR, Oct 2023

Bib

@article{Ao2023,
  author = {Ao, Junyi and Yildirim, Mehmet Sinan and Ge, Meng and Wang, Shuai and Tao, Ruijie and Qian, Yanmin and Deng, Liqun and Xiao, Longshuai and Li, Haizhou},
  journal = {CoRR},
  title = {{USED:} Universal Speaker Extraction and Diarization},
  year = {2023},
  volume = {abs/2309.10674},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2309-10674.bib},
  doi = {10.48550/ARXIV.2309.10674},
  eprint = {2309.10674},
  timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2309.10674}
}

Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition

Shuai Wang , Qibing Bai , Qi Liu , Jianwei Yu , Zhengyang Chen , Bing Han , Yanmin Qian , and Haizhou Li

CoRR, Oct 2023

Bib

@article{Wang2023c,
  author = {Wang, Shuai and Bai, Qibing and Liu, Qi and Yu, Jianwei and Chen, Zhengyang and Han, Bing and Qian, Yanmin and Li, Haizhou},
  journal = {CoRR},
  title = {Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition},
  year = {2023},
  volume = {abs/2309.11730},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2309-11730.bib},
  doi = {10.48550/ARXIV.2309.11730},
  eprint = {2309.11730},
  timestamp = {Tue, 26 Sep 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2309.11730}
}

The second multi-channel multi-party meeting transcription challenge (M2MeT) 2.0): A benchmark for speaker-attributed ASR

Yuhao Liang , Mohan Shi , Fan Yu , Yangze Li , Shiliang Zhang , Zhihao Du , Qian Chen , Lei Xie , Yanmin Qian , Jian Wu , Zhuo Chen , Kong Aik Lee , Zhijie Yan , and Hui Bu

CoRR, Oct 2023

Bib

@article{Liang2023,
  author = {Liang, Yuhao and Shi, Mohan and Yu, Fan and Li, Yangze and Zhang, Shiliang and Du, Zhihao and Chen, Qian and Xie, Lei and Qian, Yanmin and Wu, Jian and Chen, Zhuo and Lee, Kong Aik and Yan, Zhijie and Bu, Hui},
  journal = {CoRR},
  title = {The second multi-channel multi-party meeting transcription challenge (M2MeT) 2.0): {A} benchmark for speaker-attributed {ASR}},
  year = {2023},
  volume = {abs/2309.13573},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2309-13573.bib},
  doi = {10.48550/ARXIV.2309.13573},
  eprint = {2309.13573},
  timestamp = {Wed, 27 Sep 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2309.13573}
}

Diffusion Conditional Expectation Model for Efficient and Robust Target Speech Extraction

Leying Zhang , Yao Qian , Linfeng Yu , Heming Wang , Xinkai Wang , Hemin Yang , Long Zhou , Shujie Liu , Yanmin Qian , and Michael Zeng

CoRR, Oct 2023

Bib

@article{Zhang2023b,
  author = {Zhang, Leying and Qian, Yao and Yu, Linfeng and Wang, Heming and Wang, Xinkai and Yang, Hemin and Zhou, Long and Liu, Shujie and Qian, Yanmin and Zeng, Michael},
  journal = {CoRR},
  title = {Diffusion Conditional Expectation Model for Efficient and Robust Target Speech Extraction},
  year = {2023},
  volume = {abs/2309.13874},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2309-13874.bib},
  doi = {10.48550/ARXIV.2309.13874},
  eprint = {2309.13874},
  timestamp = {Sat, 21 Oct 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2309.13874}
}

Toward Universal Speech Enhancement for Diverse Input Conditions

Wangyou Zhang , Kohei Saijo , Zhong-Qiu Wang , Shinji Watanabe , and Yanmin Qian

CoRR, Oct 2023

Bib

@article{Zhang2023c,
  author = {Zhang, Wangyou and Saijo, Kohei and Wang, Zhong{-}Qiu and Watanabe, Shinji and Qian, Yanmin},
  journal = {CoRR},
  title = {Toward Universal Speech Enhancement for Diverse Input Conditions},
  year = {2023},
  volume = {abs/2309.17384},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2309-17384.bib},
  doi = {10.48550/ARXIV.2309.17384},
  eprint = {2309.17384},
  timestamp = {Tue, 17 Oct 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2309.17384}
}

One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models

Hang Shao , Bei Liu , and Yanmin Qian

CoRR, Oct 2023

Bib

@article{Shao2023b,
  author = {Shao, Hang and Liu, Bei and Qian, Yanmin},
  journal = {CoRR},
  title = {One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models},
  year = {2023},
  volume = {abs/2310.09499},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2310-09499.bib},
  doi = {10.48550/ARXIV.2310.09499},
  eprint = {2310.09499},
  timestamp = {Wed, 25 Oct 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2310.09499}
}

FAT-HuBERT: Front-end Adaptive Training of Hidden-unit BERT for Distortion-Invariant Robust Speech Recognition

Dongning Yang , Wei Wang , and Yanmin Qian

CoRR, Oct 2023

Bib

@article{Yang2023,
  author = {Yang, Dongning and Wang, Wei and Qian, Yanmin},
  journal = {CoRR},
  title = {FAT-HuBERT: Front-end Adaptive Training of Hidden-unit {BERT} for Distortion-Invariant Robust Speech Recognition},
  year = {2023},
  volume = {abs/2311.17790},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2311-17790.bib},
  doi = {10.48550/ARXIV.2311.17790},
  eprint = {2311.17790},
  timestamp = {Tue, 05 Dec 2023 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2311.17790}
}

Speaker Adaptive Text-to-Speech With Timbre-Normalized Vector-Quantized Feature

Chenpeng Du , Yiwei Guo , Xie Chen, and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2023

Bib

@article{Du2023,
  author = {Du, Chenpeng and Guo, Yiwei and Chen, Xie and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Speaker Adaptive Text-to-Speech With Timbre-Normalized Vector-Quantized Feature},
  year = {2023},
  pages = {3446--3456},
  volume = {31},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/DuGCY23.bib},
  doi = {10.1109/TASLP.2023.3308374},
  timestamp = {Thu, 09 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2023.3308374}
}

Fast-Hubert: an Efficient Training Framework for Self-Supervised Speech Representation Learning

Guanrou Yang , Ziyang Ma , Zhisheng Zheng , Yakun Song , Zhikang Niu , and Xie Chen

In IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023, Taipei, Taiwan, December 16-20, 2023 , Oct 2023

Bib

@inproceedings{Yang2023a,
  author = {Yang, Guanrou and Ma, Ziyang and Zheng, Zhisheng and Song, Yakun and Niu, Zhikang and Chen, Xie},
  booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU} 2023, Taipei, Taiwan, December 16-20, 2023},
  title = {Fast-Hubert: an Efficient Training Framework for Self-Supervised Speech Representation Learning},
  year = {2023},
  pages = {1--7},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/asru/YangMZSNC23.bib},
  doi = {10.1109/ASRU57964.2023.10389778},
  timestamp = {Tue, 13 Feb 2024 21:21:14 +0100},
  url = {https://doi.org/10.1109/ASRU57964.2023.10389778}
}

Improving Few-Shot Learning for Talking Face System with TTS Data Augmentation

Qi Chen , Ziyang Ma , Tao Liu , Xu Tan , Qu Lu , Kai Yu , and Xie Chen

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , Oct 2023

Bib

@inproceedings{Chen2023b,
  author = {Chen, Qi and Ma, Ziyang and Liu, Tao and Tan, Xu and Lu, Qu and Yu, Kai and Chen, Xie},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {Improving Few-Shot Learning for Talking Face System with {TTS} Data Augmentation},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ChenMLTLYC23.bib},
  doi = {10.1109/ICASSP49357.2023.10094777},
  timestamp = {Sun, 05 Nov 2023 16:51:21 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10094777}
}

Front-End Adapter: Adapting Front-End Input of Speech Based Self-Supervised Learning for Speech Recognition

Xie Chen, Ziyang Ma , Changli Tang , Yujin Wang , and Zhisheng Zheng

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , Oct 2023

Bib

@inproceedings{Chen2023c,
  author = {Chen, Xie and Ma, Ziyang and Tang, Changli and Wang, Yujin and Zheng, Zhisheng},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {Front-End Adapter: Adapting Front-End Input of Speech Based Self-Supervised Learning for Speech Recognition},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ChenMTWZ23.bib},
  doi = {10.1109/ICASSP49357.2023.10095130},
  timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10095130}
}

Emodiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance

Yiwei Guo , Chenpeng Du , Xie Chen, and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , Oct 2023

Bib

@inproceedings{Guo2023,
  author = {Guo, Yiwei and Du, Chenpeng and Chen, Xie and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {Emodiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/GuoDCY23.bib},
  doi = {10.1109/ICASSP49357.2023.10095621},
  timestamp = {Fri, 10 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10095621}
}

DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder

Chenpeng Du , Qi Chen , Tianyu He , Xu Tan , Xie Chen, Kai Yu, Sheng Zhao , and Jiang Bian

In Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON, Canada, 29 October 2023- 3 November 2023 , Oct 2023

Bib

@inproceedings{Du2023a,
  author = {Du, Chenpeng and Chen, Qi and He, Tianyu and Tan, Xu and Chen, Xie and Yu, Kai and Zhao, Sheng and Bian, Jiang},
  booktitle = {Proceedings of the 31st {ACM} International Conference on Multimedia, {MM} 2023, Ottawa, ON, Canada, 29 October 2023- 3 November 2023},
  title = {DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder},
  year = {2023},
  editor = {El{-}Saddik, Abdulmotaleb and Mei, Tao and Cucchiara, Rita and Bertini, Marco and Vallejo, Diana Patricia Tobon and Atrey, Pradeep K. and Hossain, M. Shamim},
  pages = {4281--4289},
  publisher = {{ACM}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/mm/DuCHT00Z023.bib},
  doi = {10.1145/3581783.3613753},
  timestamp = {Mon, 27 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1145/3581783.3613753}
}

Blank-regularized CTC for Frame Skipping in Neural Transducer

Yifan Yang , Xiaoyu Yang , Liyong Guo , Zengwei Yao , Wei Kang , Fangjun Kuang , Long Lin , Xie Chen, and Daniel Povey

CoRR, Oct 2023

Bib

@article{Yang2023b,
  author = {Yang, Yifan and Yang, Xiaoyu and Guo, Liyong and Yao, Zengwei and Kang, Wei and Kuang, Fangjun and Lin, Long and Chen, Xie and Povey, Daniel},
  journal = {CoRR},
  title = {Blank-regularized {CTC} for Frame Skipping in Neural Transducer},
  year = {2023},
  volume = {abs/2305.11558},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2305-11558.bib},
  doi = {10.48550/ARXIV.2305.11558},
  eprint = {2305.11558},
  timestamp = {Wed, 20 Sep 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2305.11558}
}

UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding

Chenpeng Du , Yiwei Guo , Feiyu Shen , Zhijun Liu , Zheng Liang , Xie Chen, Shuai Wang , Hui Zhang , and Kai Yu

CoRR, Oct 2023

Bib

@article{Du2023c,
  author = {Du, Chenpeng and Guo, Yiwei and Shen, Feiyu and Liu, Zhijun and Liang, Zheng and Chen, Xie and Wang, Shuai and Zhang, Hui and Yu, Kai},
  journal = {CoRR},
  title = {UniCATS: {A} Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding},
  year = {2023},
  volume = {abs/2306.07547},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2306-07547.bib},
  doi = {10.48550/ARXIV.2306.07547},
  eprint = {2306.07547},
  timestamp = {Sat, 17 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2306.07547}
}

Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentation

Zheng Liang , Zheshu Song , Ziyang Ma , Chenpeng Du , Kai Yu , and Xie Chen

CoRR, Oct 2023

Bib

@article{Liang2023a,
  author = {Liang, Zheng and Song, Zheshu and Ma, Ziyang and Du, Chenpeng and Yu, Kai and Chen, Xie},
  journal = {CoRR},
  title = {Improving Code-Switching and Named Entity Recognition in {ASR} with Speech Editing based Data Augmentation},
  year = {2023},
  volume = {abs/2306.08588},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2306-08588.bib},
  doi = {10.48550/ARXIV.2306.08588},
  eprint = {2306.08588},
  timestamp = {Sun, 18 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2306.08588}
}

Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation

Ziyang Ma , Zhisheng Zheng , Guanrou Yang , Yu Wang , Chao Zhang , and Xie Chen

CoRR, Oct 2023

Bib

@article{Ma2023,
  author = {Ma, Ziyang and Zheng, Zhisheng and Yang, Guanrou and Wang, Yu and Zhang, Chao and Chen, Xie},
  journal = {CoRR},
  title = {Pushing the Limits of Unsupervised Unit Discovery for {SSL} Speech Representation},
  year = {2023},
  volume = {abs/2306.08920},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2306-08920.bib},
  doi = {10.48550/ARXIV.2306.08920},
  eprint = {2306.08920},
  timestamp = {Sun, 18 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2306.08920}
}

Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems

Mingyu Cui , Jiawen Kang , Jiajun Deng , Xi Yin , Yutao Xie , Xie Chen, and Xunying Liu

CoRR, Oct 2023

Bib

@article{Cui2023,
  author = {Cui, Mingyu and Kang, Jiawen and Deng, Jiajun and Yin, Xi and Xie, Yutao and Chen, Xie and Liu, Xunying},
  journal = {CoRR},
  title = {Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems},
  year = {2023},
  volume = {abs/2306.13307},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2306-13307.bib},
  doi = {10.48550/ARXIV.2306.13307},
  eprint = {2306.13307},
  timestamp = {Tue, 04 Jul 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2306.13307}
}

DSE-TTS: Dual Speaker Embedding for Cross-Lingual Text-to-Speech

Sen Liu , Yiwei Guo , Chenpeng Du , Xie Chen, and Kai Yu

CoRR, Oct 2023

Bib

@article{Liu2023a,
  author = {Liu, Sen and Guo, Yiwei and Du, Chenpeng and Chen, Xie and Yu, Kai},
  journal = {CoRR},
  title = {{DSE-TTS:} Dual Speaker Embedding for Cross-Lingual Text-to-Speech},
  year = {2023},
  volume = {abs/2306.14145},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2306-14145.bib},
  doi = {10.48550/ARXIV.2306.14145},
  eprint = {2306.14145},
  timestamp = {Tue, 27 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2306.14145}
}

Unsupervised Active Learning: Optimizing Labeling Cost-Effectiveness for Automatic Speech Recognition

Zhisheng Zheng , Ziyang Ma , Yu Wang , and Xie Chen

CoRR, Oct 2023

Bib

@article{Zheng2023,
  author = {Zheng, Zhisheng and Ma, Ziyang and Wang, Yu and Chen, Xie},
  journal = {CoRR},
  title = {Unsupervised Active Learning: Optimizing Labeling Cost-Effectiveness for Automatic Speech Recognition},
  year = {2023},
  volume = {abs/2308.14814},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2308-14814.bib},
  doi = {10.48550/ARXIV.2308.14814},
  eprint = {2308.14814},
  timestamp = {Fri, 01 Sep 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2308.14814}
}

VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching

Yiwei Guo , Chenpeng Du , Ziyang Ma , Xie Chen, and Kai Yu

CoRR, Oct 2023

Bib

@article{Guo2023a,
  author = {Guo, Yiwei and Du, Chenpeng and Ma, Ziyang and Chen, Xie and Yu, Kai},
  journal = {CoRR},
  title = {VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching},
  year = {2023},
  volume = {abs/2309.05027},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2309-05027.bib},
  doi = {10.48550/ARXIV.2309.05027},
  eprint = {2309.05027},
  timestamp = {Wed, 20 Sep 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2309.05027}
}

Towards Universal Speech Discrete Tokens: A Case Study for ASR and TTS

Yifan Yang , Feiyu Shen , Chenpeng Du , Ziyang Ma , Kai Yu, Daniel Povey , and Xie Chen

CoRR, Oct 2023

Bib

@article{Yang2023c,
  author = {Yang, Yifan and Shen, Feiyu and Du, Chenpeng and Ma, Ziyang and Yu, Kai and Povey, Daniel and Chen, Xie},
  journal = {CoRR},
  title = {Towards Universal Speech Discrete Tokens: {A} Case Study for {ASR} and {TTS}},
  year = {2023},
  volume = {abs/2309.07377},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2309-07377.bib},
  doi = {10.48550/ARXIV.2309.07377},
  eprint = {2309.07377},
  timestamp = {Wed, 20 Sep 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2309.07377}
}

Incorporating Class-based Language Model for Named Entity Recognition in Factorized Neural Transducer

Peng Wang , Yifan Yang , Zheng Liang , Tian Tan , Shiliang Zhang , and Xie Chen

CoRR, Oct 2023

Bib

@article{Wang2023d,
  author = {Wang, Peng and Yang, Yifan and Liang, Zheng and Tan, Tian and Zhang, Shiliang and Chen, Xie},
  journal = {CoRR},
  title = {Incorporating Class-based Language Model for Named Entity Recognition in Factorized Neural Transducer},
  year = {2023},
  volume = {abs/2309.07648},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2309-07648.bib},
  doi = {10.48550/ARXIV.2309.07648},
  eprint = {2309.07648},
  timestamp = {Thu, 18 Jan 2024 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2309.07648}
}

Improved Factorized Neural Transducer Model For text-only Domain Adaptation

Junzhe Liu , Jianwei Yu , and Xie Chen

CoRR, Oct 2023

Bib

@article{Liu2023b,
  author = {Liu, Junzhe and Yu, Jianwei and Chen, Xie},
  journal = {CoRR},
  title = {Improved Factorized Neural Transducer Model For text-only Domain Adaptation},
  year = {2023},
  volume = {abs/2309.09524},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2309-09524.bib},
  doi = {10.48550/ARXIV.2309.09524},
  eprint = {2309.09524},
  timestamp = {Fri, 22 Sep 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2309.09524}
}

Leveraging Speech PTM, Text LLM, and Emotional TTS for Speech Emotion Recognition

Ziyang Ma , Wen Wu , Zhisheng Zheng , Yiwei Guo , Qian Chen , Shiliang Zhang , and Xie Chen

CoRR, Oct 2023

Bib

@article{Ma2023a,
  author = {Ma, Ziyang and Wu, Wen and Zheng, Zhisheng and Guo, Yiwei and Chen, Qian and Zhang, Shiliang and Chen, Xie},
  journal = {CoRR},
  title = {Leveraging Speech PTM, Text LLM, and Emotional {TTS} for Speech Emotion Recognition},
  year = {2023},
  volume = {abs/2309.10294},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2309-10294.bib},
  doi = {10.48550/ARXIV.2309.10294},
  eprint = {2309.10294},
  timestamp = {Wed, 27 Sep 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2309.10294}
}

Acoustic BPE for Speech Generation with Discrete Tokens

Feiyu Shen , Yiwei Guo , Chenpeng Du , Xie Chen, and Kai Yu

CoRR, Oct 2023

Bib

@article{Shen2023,
  author = {Shen, Feiyu and Guo, Yiwei and Du, Chenpeng and Chen, Xie and Yu, Kai},
  journal = {CoRR},
  title = {Acoustic {BPE} for Speech Generation with Discrete Tokens},
  year = {2023},
  volume = {abs/2310.14580},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2310-14580.bib},
  doi = {10.48550/ARXIV.2310.14580},
  eprint = {2310.14580},
  timestamp = {Mon, 30 Oct 2023 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2310.14580}
}

Expressive TTS Driven by Natural Language Prompts Using Few Human Annotations

Hanglei Zhang , Yiwei Guo , Sen Liu , Xie Chen, and Kai Yu

CoRR, Oct 2023

Bib

@article{Zhang2023d,
  author = {Zhang, Hanglei and Guo, Yiwei and Liu, Sen and Chen, Xie and Yu, Kai},
  journal = {CoRR},
  title = {Expressive {TTS} Driven by Natural Language Prompts Using Few Human Annotations},
  year = {2023},
  volume = {abs/2311.01260},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2311-01260.bib},
  doi = {10.48550/ARXIV.2311.01260},
  eprint = {2311.01260},
  timestamp = {Wed, 08 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2311.01260}
}

emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation

Ziyang Ma , Zhisheng Zheng , Jiaxin Ye , Jinchao Li , Zhifu Gao , Shiliang Zhang , and Xie Chen

CoRR, Oct 2023

Bib

@article{Ma2023b,
  author = {Ma, Ziyang and Zheng, Zhisheng and Ye, Jiaxin and Li, Jinchao and Gao, Zhifu and Zhang, Shiliang and Chen, Xie},
  journal = {CoRR},
  title = {emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation},
  year = {2023},
  volume = {abs/2312.15185},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2312-15185.bib},
  doi = {10.48550/ARXIV.2312.15185},
  eprint = {2312.15185},
  timestamp = {Thu, 18 Jan 2024 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2312.15185}
}

OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue

Zhi Chen , Yuncong Liu , Lu Chen , Su Zhu , Mengyue Wu, and Kai Yu

Trans. Assoc. Comput. Linguistics, Oct 2023

Bib

@article{Chen2023f,
  author = {Chen, Zhi and Liu, Yuncong and Chen, Lu and Zhu, Su and Wu, Mengyue and Yu, Kai},
  journal = {Trans. Assoc. Comput. Linguistics},
  title = {{OPAL:} Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue},
  year = {2023},
  pages = {68--84},
  volume = {11},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/tacl/ChenLCZWY23.bib},
  timestamp = {Mon, 27 Feb 2023 00:00:00 +0100},
  url = {https://transacl.org/ojs/index.php/tacl/article/view/4067}
}

Transcribing Vocal Communications of Domestic Shiba lnu Dogs

Jieyi Huang , Chunhao Zhang , Mengyue Wu , and Kenny Q. Zhu

In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023 , Oct 2023

Bib

@inproceedings{Huang2023,
  author = {Huang, Jieyi and Zhang, Chunhao and Wu, Mengyue and Zhu, Kenny Q.},
  booktitle = {Findings of the Association for Computational Linguistics: {ACL} 2023, Toronto, Canada, July 9-14, 2023},
  title = {Transcribing Vocal Communications of Domestic Shiba lnu Dogs},
  year = {2023},
  editor = {Rogers, Anna and Boyd{-}Graber, Jordan L. and Okazaki, Naoaki},
  pages = {13819--13832},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/acl/HuangZWZ23.bib},
  doi = {10.18653/V1/2023.FINDINGS-ACL.869},
  timestamp = {Mon, 11 Dec 2023 00:00:00 +0100},
  url = {https://doi.org/10.18653/v1/2023.findings-acl.869}
}

Detection of Multiple Mental Disorders from Social Media with Two-Stream Psychiatric Experts

Siyuan Chen , Zhiling Zhang , Mengyue Wu , and Kenny Q. Zhu

In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023 , Oct 2023

Bib

@inproceedings{Chen2023g,
  author = {Chen, Siyuan and Zhang, Zhiling and Wu, Mengyue and Zhu, Kenny Q.},
  booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, {EMNLP} 2023, Singapore, December 6-10, 2023},
  title = {Detection of Multiple Mental Disorders from Social Media with Two-Stream Psychiatric Experts},
  year = {2023},
  editor = {Bouamor, Houda and Pino, Juan and Bali, Kalika},
  pages = {9071--9084},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/emnlp/ChenZWZ23.bib},
  timestamp = {Wed, 13 Dec 2023 17:20:20 +0100},
  url = {https://aclanthology.org/2023.emnlp-main.562}
}

Semantic Space Grounded Weighted Decoding for Multi-Attribute Controllable Dialogue Generation

Zhiling Zhang , Mengyue Wu , and Kenny Q. Zhu

In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023 , Oct 2023

Bib

@inproceedings{Zhang2023e,
  author = {Zhang, Zhiling and Wu, Mengyue and Zhu, Kenny Q.},
  booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, {EMNLP} 2023, Singapore, December 6-10, 2023},
  title = {Semantic Space Grounded Weighted Decoding for Multi-Attribute Controllable Dialogue Generation},
  year = {2023},
  editor = {Bouamor, Houda and Pino, Juan and Bali, Kalika},
  pages = {13230--13243},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/emnlp/ZhangWZ23.bib},
  timestamp = {Tue, 19 Dec 2023 00:00:00 +0100},
  url = {https://aclanthology.org/2023.emnlp-main.817}
}

Diverse and Vivid Sound Generation from Text Descriptions

Guangwei Li , Xuenan Xu , Lingfeng Dai , Mengyue Wu, and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , Oct 2023

Bib

@inproceedings{Li2023e,
  author = {Li, Guangwei and Xu, Xuenan and Dai, Lingfeng and Wu, Mengyue and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {Diverse and Vivid Sound Generation from Text Descriptions},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/LiXDWY23.bib},
  doi = {10.1109/ICASSP49357.2023.10096643},
  timestamp = {Sun, 05 Nov 2023 16:51:21 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10096643}
}

Investigating Pooling Strategies and Loss Functions for Weakly-Supervised Text-to-Audio Grounding via Contrastive Learning

Xuenan Xu , Mengyue Wu, and Kai Yu

In IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2023 - Workshops, Rhodes Island, Greece, June 4-10, 2023 , Oct 2023

Bib

@inproceedings{Xu2023,
  author = {Xu, Xuenan and Wu, Mengyue and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2023 - Workshops, Rhodes Island, Greece, June 4-10, 2023},
  title = {Investigating Pooling Strategies and Loss Functions for Weakly-Supervised Text-to-Audio Grounding via Contrastive Learning},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/XuWY23.bib},
  doi = {10.1109/ICASSPW59220.2023.10192960},
  timestamp = {Mon, 07 Aug 2023 15:56:26 +0200},
  url = {https://doi.org/10.1109/ICASSPW59220.2023.10192960}
}

BLAT: Bootstrapping Language-Audio Pre-training based on AudioSet Tag-guided Synthetic Data

Xuenan Xu , Zhiling Zhang , Zelin Zhou , Pingyue Zhang , Zeyu Xie , Mengyue Wu , and Kenny Q. Zhu

In Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON, Canada, 29 October 2023- 3 November 2023 , Oct 2023

Bib

@inproceedings{Xu2023a,
  author = {Xu, Xuenan and Zhang, Zhiling and Zhou, Zelin and Zhang, Pingyue and Xie, Zeyu and Wu, Mengyue and Zhu, Kenny Q.},
  booktitle = {Proceedings of the 31st {ACM} International Conference on Multimedia, {MM} 2023, Ottawa, ON, Canada, 29 October 2023- 3 November 2023},
  title = {{BLAT:} Bootstrapping Language-Audio Pre-training based on AudioSet Tag-guided Synthetic Data},
  year = {2023},
  editor = {El{-}Saddik, Abdulmotaleb and Mei, Tao and Cucchiara, Rita and Bertini, Marco and Vallejo, Diana Patricia Tobon and Atrey, Pradeep K. and Hossain, M. Shamim},
  pages = {2756--2764},
  publisher = {{ACM}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/mm/XuZZZXWZ23.bib},
  doi = {10.1145/3581783.3613820},
  timestamp = {Thu, 09 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1145/3581783.3613820}
}

LLM-empowered Chatbots for Psychiatrist and Patient Simulation: Application and Evaluation

Siyuan Chen , Mengyue Wu , Kenny Q. Zhu , Kunyao Lan , Zhiling Zhang , and Lyuchun Cui

CoRR, Oct 2023

Bib

@article{Chen2023h,
  author = {Chen, Siyuan and Wu, Mengyue and Zhu, Kenny Q. and Lan, Kunyao and Zhang, Zhiling and Cui, Lyuchun},
  journal = {CoRR},
  title = {LLM-empowered Chatbots for Psychiatrist and Patient Simulation: Application and Evaluation},
  year = {2023},
  volume = {abs/2305.13614},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2305-13614.bib},
  doi = {10.48550/ARXIV.2305.13614},
  eprint = {2305.13614},
  timestamp = {Mon, 05 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2305.13614}
}

Enhance Temporal Relations in Audio Captioning with Sound Event Detection

Zeyu Xie , Xuenan Xu , Mengyue Wu, and Kai Yu

CoRR, Oct 2023

Bib

@article{Xie2023,
  author = {Xie, Zeyu and Xu, Xuenan and Wu, Mengyue and Yu, Kai},
  journal = {CoRR},
  title = {Enhance Temporal Relations in Audio Captioning with Sound Event Detection},
  year = {2023},
  volume = {abs/2306.01533},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2306-01533.bib},
  doi = {10.48550/ARXIV.2306.01533},
  eprint = {2306.01533},
  timestamp = {Mon, 12 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2306.01533}
}

Improving Audio Caption Fluency with Automatic Error Correction

Hanxue Zhang , Zeyu Xie , Xuenan Xu , Mengyue Wu, and Kai Yu

CoRR, Oct 2023

Bib

@article{Zhang2023g,
  author = {Zhang, Hanxue and Xie, Zeyu and Xu, Xuenan and Wu, Mengyue and Yu, Kai},
  journal = {CoRR},
  title = {Improving Audio Caption Fluency with Automatic Error Correction},
  year = {2023},
  volume = {abs/2306.10090},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2306-10090.bib},
  doi = {10.48550/ARXIV.2306.10090},
  eprint = {2306.10090},
  timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2306.10090}
}

A Large-scale Dataset for Audio-Language Representation Learning

Luoyi Sun , Xuenan Xu , Mengyue Wu, and Weidi Xie

CoRR, Oct 2023

Bib

@article{Sun2023,
  author = {Sun, Luoyi and Xu, Xuenan and Wu, Mengyue and Xie, Weidi},
  journal = {CoRR},
  title = {A Large-scale Dataset for Audio-Language Representation Learning},
  year = {2023},
  volume = {abs/2309.11500},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2309-11500.bib},
  doi = {10.48550/ARXIV.2309.11500},
  eprint = {2309.11500},
  timestamp = {Mon, 25 Sep 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2309.11500}
}

Does My Dog "Speak" Like Me? The Acoustic Correlation between Pet Dogs and Their Human Owners

Jieyi Huang , Chunhao Zhang , Yufei Wang , Mengyue Wu , and Kenny Q. Zhu

CoRR, Oct 2023

Bib

@article{Huang2023a,
  author = {Huang, Jieyi and Zhang, Chunhao and Wang, Yufei and Wu, Mengyue and Zhu, Kenny Q.},
  journal = {CoRR},
  title = {Does My Dog "Speak" Like Me? The Acoustic Correlation between Pet Dogs and Their Human Owners},
  year = {2023},
  volume = {abs/2309.13085},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2309-13085.bib},
  doi = {10.48550/ARXIV.2309.13085},
  eprint = {2309.13085},
  timestamp = {Mon, 11 Dec 2023 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2309.13085}
}

Towards Lexical Analysis of Dog Vocalizations via Online Videos

Yufei Wang , Chunhao Zhang , Jieyi Huang , Mengyue Wu , and Kenny Q. Zhu

CoRR, Oct 2023

Bib

@article{Wang2023e,
  author = {Wang, Yufei and Zhang, Chunhao and Huang, Jieyi and Wu, Mengyue and Zhu, Kenny Q.},
  journal = {CoRR},
  title = {Towards Lexical Analysis of Dog Vocalizations via Online Videos},
  year = {2023},
  volume = {abs/2309.13086},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2309-13086.bib},
  doi = {10.48550/ARXIV.2309.13086},
  eprint = {2309.13086},
  timestamp = {Mon, 11 Dec 2023 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2309.13086}
}

PsyEval: A Comprehensive Large Language Model Evaluation Benchmark for Mental Health

Haoan Jin , Siyuan Chen , Mengyue Wu , and Kenny Q. Zhu

CoRR, Oct 2023

Bib

@article{Jin2023,
  author = {Jin, Haoan and Chen, Siyuan and Wu, Mengyue and Zhu, Kenny Q.},
  journal = {CoRR},
  title = {PsyEval: {A} Comprehensive Large Language Model Evaluation Benchmark for Mental Health},
  year = {2023},
  volume = {abs/2311.09189},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2311-09189.bib},
  doi = {10.48550/ARXIV.2311.09189},
  eprint = {2311.09189},
  timestamp = {Tue, 21 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2311.09189}
}

A Heterogeneous Graph to Abstract Syntax Tree Framework for Text-to-SQL

Ruisheng Cao , Lu Chen, Jieyu Li , Hanchong Zhang , Hongshen Xu , Wangyou Zhang , and Kai Yu

IEEE Trans. Pattern Anal. Mach. Intell., Oct 2023

Bib

@article{Cao2023,
  author = {Cao, Ruisheng and Chen, Lu and Li, Jieyu and Zhang, Hanchong and Xu, Hongshen and Zhang, Wangyou and Yu, Kai},
  journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.},
  title = {A Heterogeneous Graph to Abstract Syntax Tree Framework for Text-to-SQL},
  year = {2023},
  number = {11},
  pages = {13796--13813},
  volume = {45},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/pami/CaoCLZXZY23.bib},
  doi = {10.1109/TPAMI.2023.3298895},
  timestamp = {Sat, 14 Oct 2023 01:00:00 +0200},
  url = {https://doi.org/10.1109/TPAMI.2023.3298895}
}

Speech Enhancement With Integration of Neural Homomorphic Synthesis and Spectral Masking

Wenbin Jiang , and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2023

Bib

@article{Jiang2023,
  author = {Jiang, Wenbin and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Speech Enhancement With Integration of Neural Homomorphic Synthesis and Spectral Masking},
  year = {2023},
  pages = {1758--1770},
  volume = {31},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/JiangY23.bib},
  doi = {10.1109/TASLP.2023.3271151},
  timestamp = {Sun, 22 Oct 2023 01:00:00 +0200},
  url = {https://doi.org/10.1109/TASLP.2023.3271151}
}

SPM: A Split-Parsing Method for Joint Multi-Intent Detection and Slot Filling

Sheng Jiang , Su Zhu , Ruisheng Cao , Qingliang Miao , and Kai Yu

In Proceedings of the The 61st Annual Meeting of the Association for Computational Linguistics: Industry Track, ACL 2023, Toronto, Canada, July 9-14, 2023 , Oct 2023

Bib

@inproceedings{Jiang2023a,
  author = {Jiang, Sheng and Zhu, Su and Cao, Ruisheng and Miao, Qingliang and Yu, Kai},
  booktitle = {Proceedings of the The 61st Annual Meeting of the Association for Computational Linguistics: Industry Track, {ACL} 2023, Toronto, Canada, July 9-14, 2023},
  title = {{SPM:} {A} Split-Parsing Method for Joint Multi-Intent Detection and Slot Filling},
  year = {2023},
  editor = {Sitaram, Sunayana and Klebanov, Beata Beigman and Williams, Jason D.},
  pages = {668--675},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/acl/JiangZCM023.bib},
  doi = {10.18653/V1/2023.ACL-INDUSTRY.64},
  timestamp = {Thu, 10 Aug 2023 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/2023.acl-industry.64}
}

Exploring Schema Generalizability of Text-to-SQL

Jieyu Li , Lu Chen, Ruisheng Cao , Su Zhu , Hongshen Xu , Zhi Chen , Hanchong Zhang , and Kai Yu

In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023 , Oct 2023

Bib

@inproceedings{Li2023g,
  author = {Li, Jieyu and Chen, Lu and Cao, Ruisheng and Zhu, Su and Xu, Hongshen and Chen, Zhi and Zhang, Hanchong and Yu, Kai},
  booktitle = {Findings of the Association for Computational Linguistics: {ACL} 2023, Toronto, Canada, July 9-14, 2023},
  title = {Exploring Schema Generalizability of Text-to-SQL},
  year = {2023},
  editor = {Rogers, Anna and Boyd{-}Graber, Jordan L. and Okazaki, Naoaki},
  pages = {1344--1360},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/acl/LiCCZX0Z023.bib},
  doi = {10.18653/V1/2023.FINDINGS-ACL.87},
  timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
  url = {https://doi.org/10.18653/v1/2023.findings-acl.87}
}

TeCS: A Dataset and Benchmark for Tense Consistency of Machine Translation

Yiming Ai , Zhiwei He , Kai Yu, and Rui Wang

In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), ACL 2023, Toronto, Canada, July 9-14, 2023 , Oct 2023

Bib

@inproceedings{Ai2023,
  author = {Ai, Yiming and He, Zhiwei and Yu, Kai and Wang, Rui},
  booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), {ACL} 2023, Toronto, Canada, July 9-14, 2023},
  title = {TeCS: {A} Dataset and Benchmark for Tense Consistency of Machine Translation},
  year = {2023},
  editor = {Rogers, Anna and Boyd{-}Graber, Jordan L. and Okazaki, Naoaki},
  pages = {1930--1941},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/acl/Ai00W23.bib},
  doi = {10.18653/V1/2023.ACL-SHORT.164},
  timestamp = {Thu, 07 Dec 2023 00:00:00 +0100},
  url = {https://doi.org/10.18653/v1/2023.acl-short.164}
}

CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset

Hanchong Zhang , Jieyu Li , Lu Chen, Ruisheng Cao , Yunyan Zhang , Yu Huang , Yefeng Zheng , and Kai Yu

In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023 , Oct 2023

Bib

@inproceedings{Zhang2023h,
  author = {Zhang, Hanchong and Li, Jieyu and Chen, Lu and Cao, Ruisheng and Zhang, Yunyan and Huang, Yu and Zheng, Yefeng and Yu, Kai},
  booktitle = {Findings of the Association for Computational Linguistics: {ACL} 2023, Toronto, Canada, July 9-14, 2023},
  title = {{CSS:} {A} Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset},
  year = {2023},
  editor = {Rogers, Anna and Boyd{-}Graber, Jordan L. and Okazaki, Naoaki},
  pages = {6970--6983},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/acl/ZhangLCCZH0023.bib},
  doi = {10.18653/V1/2023.FINDINGS-ACL.435},
  timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
  url = {https://doi.org/10.18653/v1/2023.findings-acl.435}
}

ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought

Hanchong Zhang , Ruisheng Cao , Lu Chen, Hongshen Xu , and Kai Yu

In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023 , Oct 2023

Bib

@inproceedings{Zhang2023i,
  author = {Zhang, Hanchong and Cao, Ruisheng and Chen, Lu and Xu, Hongshen and Yu, Kai},
  booktitle = {Findings of the Association for Computational Linguistics: {EMNLP} 2023, Singapore, December 6-10, 2023},
  title = {{ACT-SQL:} In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought},
  year = {2023},
  editor = {Bouamor, Houda and Pino, Juan and Bali, Kalika},
  pages = {3501--3532},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/emnlp/ZhangCCX023.bib},
  timestamp = {Wed, 13 Dec 2023 17:20:20 +0100},
  url = {https://aclanthology.org/2023.findings-emnlp.227}
}

Multi-Speaker Multi-Lingual VQTTS System for LIMMITS 2023 Challenge

Chenpeng Du , Yiwei Guo , Feiyu Shen , and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , Oct 2023

Bib

@inproceedings{Du2023d,
  author = {Du, Chenpeng and Guo, Yiwei and Shen, Feiyu and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {Multi-Speaker Multi-Lingual {VQTTS} System for {LIMMITS} 2023 Challenge},
  year = {2023},
  pages = {1--2},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/DuGSY23.bib},
  doi = {10.1109/ICASSP49357.2023.10096415},
  timestamp = {Fri, 10 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10096415}
}

DiffVoice: Text-to-Speech with Latent Diffusion

Zhijun Liu , Yiwei Guo , and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023 , Oct 2023

Bib

@inproceedings{Liu2023c,
  author = {Liu, Zhijun and Guo, Yiwei and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  title = {DiffVoice: Text-to-Speech with Latent Diffusion},
  year = {2023},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/LiuGY23.bib},
  doi = {10.1109/ICASSP49357.2023.10095100},
  timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10095100}
}

Large Language Models Are Semi-Parametric Reinforcement Learning Agents

Danyang Zhang , Lu Chen, Situo Zhang , Hongshen Xu , Zihan Zhao , and Kai Yu

In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023 , Oct 2023

Bib

@inproceedings{Zhang2023j,
  author = {Zhang, Danyang and Chen, Lu and Zhang, Situo and Xu, Hongshen and Zhao, Zihan and Yu, Kai},
  booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
  title = {Large Language Models Are Semi-Parametric Reinforcement Learning Agents},
  year = {2023},
  editor = {Oh, Alice and Naumann, Tristan and Globerson, Amir and Saenko, Kate and Hardt, Moritz and Levine, Sergey},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/nips/ZhangCZXZ023.bib},
  timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
  url = {http://papers.nips.cc/paper\_files/paper/2023/hash/f6b22ac37beb5da61efd4882082c9ecd-Abstract-Conference.html}
}

Mobile-Env: A Universal Platform for Training and Evaluation of Mobile Interaction

Danyang Zhang , Lu Chen, and Kai Yu

CoRR, Oct 2023

Bib

@article{Zhang2023k,
  author = {Zhang, Danyang and Chen, Lu and Yu, Kai},
  journal = {CoRR},
  title = {Mobile-Env: {A} Universal Platform for Training and Evaluation of Mobile Interaction},
  year = {2023},
  volume = {abs/2305.08144},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2305-08144.bib},
  doi = {10.48550/ARXIV.2305.08144},
  eprint = {2305.08144},
  timestamp = {Wed, 17 May 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2305.08144}
}

SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research

Liangtai Sun , Yang Han , Zihan Zhao , Da Ma , Zhennan Shen , Baocai Chen , Lu Chen, and Kai Yu

CoRR, Oct 2023

Bib

@article{Sun2023a,
  author = {Sun, Liangtai and Han, Yang and Zhao, Zihan and Ma, Da and Shen, Zhennan and Chen, Baocai and Chen, Lu and Yu, Kai},
  journal = {CoRR},
  title = {SciEval: {A} Multi-Level Large Language Model Evaluation Benchmark for Scientific Research},
  year = {2023},
  volume = {abs/2308.13149},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2308-13149.bib},
  doi = {10.48550/ARXIV.2308.13149},
  eprint = {2308.13149},
  timestamp = {Fri, 01 Sep 2023 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2308.13149}
}

ASTormer: An AST Structure-aware Transformer Decoder for Text-to-SQL

Ruisheng Cao , Hanchong Zhang , Hongshen Xu , Jieyu Li , Da Ma , Lu Chen, and Kai Yu

CoRR, Oct 2023

Bib

@article{Cao2023a,
  author = {Cao, Ruisheng and Zhang, Hanchong and Xu, Hongshen and Li, Jieyu and Ma, Da and Chen, Lu and Yu, Kai},
  journal = {CoRR},
  title = {ASTormer: An {AST} Structure-aware Transformer Decoder for Text-to-SQL},
  year = {2023},
  volume = {abs/2310.18662},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2310-18662.bib},
  doi = {10.48550/ARXIV.2310.18662},
  eprint = {2310.18662},
  timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2310.18662}
}

DiffDub: Person-generic Visual Dubbing Using Inpainting Renderer with Diffusion Auto-encoder

Tao Liu , Chenpeng Du , Shuai Fan , Feilong Chen , and Kai Yu

CoRR, Oct 2023

Bib

@article{Liu2023e,
  author = {Liu, Tao and Du, Chenpeng and Fan, Shuai and Chen, Feilong and Yu, Kai},
  journal = {CoRR},
  title = {DiffDub: Person-generic Visual Dubbing Using Inpainting Renderer with Diffusion Auto-encoder},
  year = {2023},
  volume = {abs/2311.01811},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2311-01811.bib},
  doi = {10.48550/ARXIV.2311.01811},
  eprint = {2311.01811},
  timestamp = {Tue, 07 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2311.01811}
}

SEF-VC: Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attention

Junjie Li , Yiwei Guo , Xie Chen, and Kai Yu

CoRR, Oct 2023

Bib

@article{Li2023h,
  author = {Li, Junjie and Guo, Yiwei and Chen, Xie and Yu, Kai},
  journal = {CoRR},
  title = {{SEF-VC:} Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attention},
  year = {2023},
  volume = {abs/2312.08676},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2312-08676.bib},
  doi = {10.48550/ARXIV.2312.08676},
  eprint = {2312.08676},
  timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2312.08676}
}

2022

Heterogeneous Graph Representation for Knowledge Tracing

Jisen Chen , Jian Shen , Ting Long , Liping Shen, Weinan Zhang , and Yong Yu

In Neural Information Processing - 29th International Conference, ICONIP 2022, Virtual Event, November 22-26, 2022, Proceedings, Part I , Oct 2022

Bib

@inproceedings{Chen2022,
  author = {Chen, Jisen and Shen, Jian and Long, Ting and Shen, Liping and Zhang, Weinan and Yu, Yong},
  booktitle = {Neural Information Processing - 29th International Conference, {ICONIP} 2022, Virtual Event, November 22-26, 2022, Proceedings, Part {I}},
  title = {Heterogeneous Graph Representation for Knowledge Tracing},
  year = {2022},
  editor = {Tanveer, Mohammad and Agarwal, Sonali and Ozawa, Seiichi and Ekbal, Asif and Jatowt, Adam},
  pages = {224--235},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  volume = {13623},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iconip/ChenSLS0022.bib},
  doi = {10.1007/978-3-031-30105-6\_19},
  timestamp = {Thu, 20 Apr 2023 15:23:54 +0200},
  url = {https://doi.org/10.1007/978-3-031-30105-6\_19}
}

A simple but practical method: How to improve the usage of entities in the Chinese question generation

Haoze Yang , Kunyao Lan , Jiawei You , and Liping Shen

In International Joint Conference on Neural Networks, IJCNN 2022, Padua, Italy, July 18-23, 2022 , Oct 2022

Bib

@inproceedings{Yang2022,
  author = {Yang, Haoze and Lan, Kunyao and You, Jiawei and Shen, Liping},
  booktitle = {International Joint Conference on Neural Networks, {IJCNN} 2022, Padua, Italy, July 18-23, 2022},
  title = {A simple but practical method: How to improve the usage of entities in the Chinese question generation},
  year = {2022},
  pages = {1--8},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/ijcnn/YangLYS22.bib},
  doi = {10.1109/IJCNN55064.2022.9891960},
  timestamp = {Mon, 10 Oct 2022 17:40:09 +0200},
  url = {https://doi.org/10.1109/IJCNN55064.2022.9891960}
}

From Uniform Models To Generic Representations: Stock Return Prediction With Pre-training

Jiawei You , Tianyuan Han , and Liping Shen

In International Joint Conference on Neural Networks, IJCNN 2022, Padua, Italy, July 18-23, 2022 , Oct 2022

Bib

@inproceedings{You2022,
  author = {You, Jiawei and Han, Tianyuan and Shen, Liping},
  booktitle = {International Joint Conference on Neural Networks, {IJCNN} 2022, Padua, Italy, July 18-23, 2022},
  title = {From Uniform Models To Generic Representations: Stock Return Prediction With Pre-training},
  year = {2022},
  pages = {1--8},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/ijcnn/YouHS22.bib},
  doi = {10.1109/IJCNN55064.2022.9892697},
  timestamp = {Mon, 10 Oct 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/IJCNN55064.2022.9892697}
}

WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing

Sanyuan Chen , Chengyi Wang , Zhengyang Chen , Yu Wu , Shujie Liu , Zhuo Chen , Jinyu Li , Naoyuki Kanda , Takuya Yoshioka , Xiong Xiao , Jian Wu , Long Zhou , Shuo Ren , Yanmin Qian , Yao Qian , Jian Wu , Michael Zeng , Xiangzhan Yu , and Furu Wei

IEEE J. Sel. Top. Signal Process., Oct 2022

Bib

@article{Chen2022a,
  author = {Chen, Sanyuan and Wang, Chengyi and Chen, Zhengyang and Wu, Yu and Liu, Shujie and Chen, Zhuo and Li, Jinyu and Kanda, Naoyuki and Yoshioka, Takuya and Xiao, Xiong and Wu, Jian and Zhou, Long and Ren, Shuo and Qian, Yanmin and Qian, Yao and Wu, Jian and Zeng, Michael and Yu, Xiangzhan and Wei, Furu},
  journal = {{IEEE} J. Sel. Top. Signal Process.},
  title = {WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing},
  year = {2022},
  number = {6},
  pages = {1505--1518},
  volume = {16},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/jstsp/ChenWCWLCLKYXWZ22.bib},
  doi = {10.1109/JSTSP.2022.3188113},
  timestamp = {Sun, 13 Nov 2022 00:00:00 +0100},
  url = {https://doi.org/10.1109/JSTSP.2022.3188113}
}

Optimizing Data Usage for Low-Resource Speech Recognition

Yanmin Qian , and Zhikai Zhou

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2022

Bib

@article{Qian2022,
  author = {Qian, Yanmin and Zhou, Zhikai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Optimizing Data Usage for Low-Resource Speech Recognition},
  year = {2022},
  pages = {394--403},
  volume = {30},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/QianZ22.bib},
  doi = {10.1109/TASLP.2022.3140552},
  timestamp = {Tue, 08 Feb 2022 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2022.3140552}
}

Dual-Path Modeling With Memory Embedding Model for Continuous Speech Separation

Chenda Li , Zhuo Chen , and Yanmin Qian

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2022

Bib

@article{Li2022,
  author = {Li, Chenda and Chen, Zhuo and Qian, Yanmin},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Dual-Path Modeling With Memory Embedding Model for Continuous Speech Separation},
  year = {2022},
  pages = {1508--1520},
  volume = {30},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/LiCQ22.bib},
  doi = {10.1109/TASLP.2022.3165712},
  timestamp = {Wed, 18 May 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/TASLP.2022.3165712}
}

Layer-Wise Fast Adaptation for End-to-End Multi-Accent Speech Recognition

Yanmin Qian , Xun Gong , and Houjun Huang

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2022

Bib

@article{Qian2022a,
  author = {Qian, Yanmin and Gong, Xun and Huang, Houjun},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Layer-Wise Fast Adaptation for End-to-End Multi-Accent Speech Recognition},
  year = {2022},
  pages = {2842--2853},
  volume = {30},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/QianGH22.bib},
  doi = {10.1109/TASLP.2022.3198546},
  timestamp = {Fri, 23 Sep 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/TASLP.2022.3198546}
}

End-to-End Dereverberation, Beamforming, and Speech Recognition in a Cocktail Party

Wangyou Zhang , Xuankai Chang , Christoph Böddeker , Tomohiro Nakatani , Shinji Watanabe , and Yanmin Qian

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2022

Bib

@article{Zhang2022,
  author = {Zhang, Wangyou and Chang, Xuankai and B{\"{o}}ddeker, Christoph and Nakatani, Tomohiro and Watanabe, Shinji and Qian, Yanmin},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {End-to-End Dereverberation, Beamforming, and Speech Recognition in a Cocktail Party},
  year = {2022},
  pages = {3173--3188},
  volume = {30},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/ZhangCBNWQ22.bib},
  doi = {10.1109/TASLP.2022.3209942},
  timestamp = {Mon, 05 Dec 2022 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2022.3209942}
}

Time-Domain Audio-Visual Speech Separation on Low Quality Videos

Yifei Wu , Chenda Li , Jinfeng Bai , Zhongqin Wu , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Wu2022,
  author = {Wu, Yifei and Li, Chenda and Bai, Jinfeng and Wu, Zhongqin and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Time-Domain Audio-Visual Speech Separation on Low Quality Videos},
  year = {2022},
  pages = {256--260},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/WuLBWQ22.bib},
  doi = {10.1109/ICASSP43922.2022.9746866},
  timestamp = {Tue, 07 Jun 2022 17:34:47 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746866}
}

Skim: Skipping Memory Lstm for Low-Latency Real-Time Continuous Speech Separation

Chenda Li , Lei Yang , Weiqin Wang , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Li2022a,
  author = {Li, Chenda and Yang, Lei and Wang, Weiqin and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Skim: Skipping Memory Lstm for Low-Latency Real-Time Continuous Speech Separation},
  year = {2022},
  pages = {681--685},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/LiYWQ22.bib},
  doi = {10.1109/ICASSP43922.2022.9746372},
  timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746372}
}

Large-Scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification

Zhengyang Chen , Sanyuan Chen , Yu Wu , Yao Qian , Chengyi Wang , Shujie Liu , Yanmin Qian , and Michael Zeng

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Chen2022b,
  author = {Chen, Zhengyang and Chen, Sanyuan and Wu, Yu and Qian, Yao and Wang, Chengyi and Liu, Shujie and Qian, Yanmin and Zeng, Michael},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Large-Scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification},
  year = {2022},
  pages = {6147--6151},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ChenCWQWLQZ22.bib},
  doi = {10.1109/ICASSP43922.2022.9747814},
  timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9747814}
}

Local Information Modeling with Self-Attention for Speaker Verification

Bing Han , Zhengyang Chen , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Han2022,
  author = {Han, Bing and Chen, Zhengyang and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Local Information Modeling with Self-Attention for Speaker Verification},
  year = {2022},
  pages = {6727--6731},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/HanCQ22.bib},
  doi = {10.1109/ICASSP43922.2022.9746050},
  timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746050}
}

Punctuation Prediction for Streaming On-Device Speech Recognition

Zhikai Zhou , Tian Tan , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Zhou2022,
  author = {Zhou, Zhikai and Tan, Tian and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Punctuation Prediction for Streaming On-Device Speech Recognition},
  year = {2022},
  pages = {7277--7281},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ZhouTQ22.bib},
  doi = {10.1109/ICASSP43922.2022.9746366},
  timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746366}
}

MLP-SVNET: A Multi-Layer Perceptrons Based Network for Speaker Verification

Bing Han , Zhengyang Chen , Bei Liu , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Han2022a,
  author = {Han, Bing and Chen, Zhengyang and Liu, Bei and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {{MLP-SVNET:} {A} Multi-Layer Perceptrons Based Network for Speaker Verification},
  year = {2022},
  pages = {7522--7526},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/HanCLQ22.bib},
  doi = {10.1109/ICASSP43922.2022.9747172},
  timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9747172}
}

Self-Knowledge Distillation via Feature Enhancement for Speaker Verification

Bei Liu , Haoyu Wang , Zhengyang Chen , Shuai Wang , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Liu2022,
  author = {Liu, Bei and Wang, Haoyu and Chen, Zhengyang and Wang, Shuai and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Self-Knowledge Distillation via Feature Enhancement for Speaker Verification},
  year = {2022},
  pages = {7542--7546},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/LiuWCWQ22.bib},
  doi = {10.1109/ICASSP43922.2022.9746529},
  timestamp = {Fri, 10 Mar 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746529}
}

Optimizing Alignment of Speech and Language Latent Spaces for End-To-End Speech Recognition and Understanding

Wei Wang , Shuo Ren , Yao Qian , Shujie Liu , Yu Shi , Yanmin Qian , and Michael Zeng

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Wang2022,
  author = {Wang, Wei and Ren, Shuo and Qian, Yao and Liu, Shujie and Shi, Yu and Qian, Yanmin and Zeng, Michael},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Optimizing Alignment of Speech and Language Latent Spaces for End-To-End Speech Recognition and Understanding},
  year = {2022},
  pages = {7802--7806},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/WangRQLSQZ22.bib},
  doi = {10.1109/ICASSP43922.2022.9747760},
  timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9747760}
}

Exploring Effective Data Utilization for Low-Resource Speech Recognition

Zhikai Zhou , Wei Wang , Wangyou Zhang , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Zhou2022a,
  author = {Zhou, Zhikai and Wang, Wei and Zhang, Wangyou and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Exploring Effective Data Utilization for Low-Resource Speech Recognition},
  year = {2022},
  pages = {8192--8196},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ZhouWZQ22.bib},
  doi = {10.1109/ICASSP43922.2022.9747543},
  timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9747543}
}

Summary on the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge

Fan Yu , Shiliang Zhang , Pengcheng Guo , Yihui Fu , Zhihao Du , Siqi Zheng , Weilong Huang , Lei Xie , Zheng-Hua Tan , DeLiang Wang , Yanmin Qian , Kong Aik Lee , Zhijie Yan , Bin Ma , Xin Xu , and Hui Bu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Yu2022,
  author = {Yu, Fan and Zhang, Shiliang and Guo, Pengcheng and Fu, Yihui and Du, Zhihao and Zheng, Siqi and Huang, Weilong and Xie, Lei and Tan, Zheng{-}Hua and Wang, DeLiang and Qian, Yanmin and Lee, Kong Aik and Yan, Zhijie and Ma, Bin and Xu, Xin and Bu, Hui},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Summary on the {ICASSP} 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge},
  year = {2022},
  pages = {9156--9160},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/YuZGFDZHXTWQLYM22.bib},
  doi = {10.1109/ICASSP43922.2022.9746270},
  timestamp = {Mon, 13 Mar 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746270}
}

The Sjtu System For Multimodal Information Based Speech Processing Challenge 2021

Wei Wang , Xun Gong , Yifei Wu , Zhikai Zhou , Chenda Li , Wangyou Zhang , Bing Han , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Wang2022a,
  author = {Wang, Wei and Gong, Xun and Wu, Yifei and Zhou, Zhikai and Li, Chenda and Zhang, Wangyou and Han, Bing and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {The Sjtu System For Multimodal Information Based Speech Processing Challenge 2021},
  year = {2022},
  pages = {9261--9265},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/WangGWZLZHQ22.bib},
  doi = {10.1109/ICASSP43922.2022.9746874},
  timestamp = {Fri, 23 Sep 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746874}
}

Attentive Feature Fusion for Robust Speaker Verification

Bei Liu , Zhengyang Chen , and Yanmin Qian

In Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022 , Oct 2022

Bib

@inproceedings{Liu2022a,
  author = {Liu, Bei and Chen, Zhengyang and Qian, Yanmin},
  booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022},
  title = {Attentive Feature Fusion for Robust Speaker Verification},
  year = {2022},
  editor = {Ko, Hanseok and Hansen, John H. L.},
  pages = {286--290},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/LiuCQ22.bib},
  doi = {10.21437/INTERSPEECH.2022-478},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2022-478}
}

Dual Path Embedding Learning for Speaker Verification with Triplet Attention

Bei Liu , Zhengyang Chen , and Yanmin Qian

In Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022 , Oct 2022

Bib

@inproceedings{Liu2022b,
  author = {Liu, Bei and Chen, Zhengyang and Qian, Yanmin},
  booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022},
  title = {Dual Path Embedding Learning for Speaker Verification with Triplet Attention},
  year = {2022},
  editor = {Ko, Hanseok and Hansen, John H. L.},
  pages = {291--295},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/LiuCQ22a.bib},
  doi = {10.21437/INTERSPEECH.2022-481},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2022-481}
}

DF-ResNet: Boosting Speaker Verification Performance with Depth-First Design

Bei Liu , Zhengyang Chen , Shuai Wang , Haoyu Wang , Bing Han , and Yanmin Qian

In Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022 , Oct 2022

Bib

@inproceedings{Liu2022c,
  author = {Liu, Bei and Chen, Zhengyang and Wang, Shuai and Wang, Haoyu and Han, Bing and Qian, Yanmin},
  booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022},
  title = {DF-ResNet: Boosting Speaker Verification Performance with Depth-First Design},
  year = {2022},
  editor = {Ko, Hanseok and Hansen, John H. L.},
  pages = {296--300},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/LiuCWWHQ22.bib},
  doi = {10.21437/INTERSPEECH.2022-484},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2022-484}
}

Enroll-Aware Attentive Statistics Pooling for Target Speaker Verification

Leying Zhang , Zhengyang Chen , and Yanmin Qian

In Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022 , Oct 2022

Bib

@inproceedings{Zhang2022a,
  author = {Zhang, Leying and Chen, Zhengyang and Qian, Yanmin},
  booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022},
  title = {Enroll-Aware Attentive Statistics Pooling for Target Speaker Verification},
  year = {2022},
  editor = {Ko, Hanseok and Hansen, John H. L.},
  pages = {311--315},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ZhangCQ22.bib},
  doi = {10.21437/INTERSPEECH.2022-645},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2022-645}
}

MSDWild: Multi-modal Speaker Diarization Dataset in the Wild

Tao Liu , Shuai Fan , Xu Xiang , Hongbo Song , Shaoxiong Lin , Jiaqi Sun , Tianyuan Han , Siyuan Chen , Binwei Yao , Sen Liu , Yifei Wu , Yanmin Qian , and Kai Yu

In Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022 , Oct 2022

Bib

@inproceedings{Liu2022d,
  author = {Liu, Tao and Fan, Shuai and Xiang, Xu and Song, Hongbo and Lin, Shaoxiong and Sun, Jiaqi and Han, Tianyuan and Chen, Siyuan and Yao, Binwei and Liu, Sen and Wu, Yifei and Qian, Yanmin and Yu, Kai},
  booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022},
  title = {MSDWild: Multi-modal Speaker Diarization Dataset in the Wild},
  year = {2022},
  editor = {Ko, Hanseok and Hansen, John H. L.},
  pages = {1476--1480},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/Liu0XSLSHCYLWQ022.bib},
  doi = {10.21437/INTERSPEECH.2022-10466},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2022-10466}
}

Knowledge Transfer and Distillation from Autoregressive to Non-Autoregessive Speech Recognition

Xun Gong , Zhikai Zhou , and Yanmin Qian

In Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022 , Oct 2022

Bib

@inproceedings{Gong2022,
  author = {Gong, Xun and Zhou, Zhikai and Qian, Yanmin},
  booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022},
  title = {Knowledge Transfer and Distillation from Autoregressive to Non-Autoregessive Speech Recognition},
  year = {2022},
  editor = {Ko, Hanseok and Hansen, John H. L.},
  pages = {2618--2622},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/0005ZQ22.bib},
  doi = {10.21437/INTERSPEECH.2022-632},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2022-632}
}

Self-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correction

Bing Han , Zhengyang Chen , and Yanmin Qian

In Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022 , Oct 2022

Bib

@inproceedings{Han2022b,
  author = {Han, Bing and Chen, Zhengyang and Qian, Yanmin},
  booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022},
  title = {Self-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correction},
  year = {2022},
  editor = {Ko, Hanseok and Hansen, John H. L.},
  pages = {4780--4784},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/HanCQ22.bib},
  doi = {10.21437/INTERSPEECH.2022-742},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2022-742}
}

Separating Long-Form Speech with Group-wise Permutation Invariant Training

Wangyou Zhang , Zhuo Chen , Naoyuki Kanda , Shujie Liu , Jinyu Li , Sefik Emre Eskimez , Takuya Yoshioka , Xiong Xiao , Zhong Meng , Yanmin Qian , and Furu Wei

In Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022 , Oct 2022

Bib

@inproceedings{Zhang2022b,
  author = {Zhang, Wangyou and Chen, Zhuo and Kanda, Naoyuki and Liu, Shujie and Li, Jinyu and Eskimez, Sefik Emre and Yoshioka, Takuya and Xiao, Xiong and Meng, Zhong and Qian, Yanmin and Wei, Furu},
  booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022},
  title = {Separating Long-Form Speech with Group-wise Permutation Invariant Training},
  year = {2022},
  editor = {Ko, Hanseok and Hansen, John H. L.},
  pages = {5383--5387},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/Zhang0K00EYXMQW22.bib},
  doi = {10.21437/INTERSPEECH.2022-10362},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2022-10362}
}

ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding

Yen-Ju Lu , Xuankai Chang , Chenda Li , Wangyou Zhang , Samuele Cornell , Zhaoheng Ni , Yoshiki Masuyama , Brian Yan , Robin Scheibler , Zhong-Qiu Wang , Yu Tsao , Yanmin Qian , and Shinji Watanabe

In Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022 , Oct 2022

Bib

@inproceedings{Lu2022,
  author = {Lu, Yen{-}Ju and Chang, Xuankai and Li, Chenda and Zhang, Wangyou and Cornell, Samuele and Ni, Zhaoheng and Masuyama, Yoshiki and Yan, Brian and Scheibler, Robin and Wang, Zhong{-}Qiu and Tsao, Yu and Qian, Yanmin and Watanabe, Shinji},
  booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022},
  title = {ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding},
  year = {2022},
  editor = {Ko, Hanseok and Hansen, John H. L.},
  pages = {5458--5462},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/LuCLZCNMYSW0Q022.bib},
  doi = {10.21437/INTERSPEECH.2022-10727},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2022-10727}
}

Improving Speech Separation with Knowledge Distilled from Self-supervised Pre-trained Models

Bowen Qu , Chenda Li , Jinfeng Bai , and Yanmin Qian

In 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022, Singapore, December 11-14, 2022 , Oct 2022

Bib

@inproceedings{Qu2022,
  author = {Qu, Bowen and Li, Chenda and Bai, Jinfeng and Qian, Yanmin},
  booktitle = {13th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2022, Singapore, December 11-14, 2022},
  title = {Improving Speech Separation with Knowledge Distilled from Self-supervised Pre-trained Models},
  year = {2022},
  editor = {Lee, Kong Aik and Lee, Hung{-}yi and Lu, Yanfeng and Dong, Minghui},
  pages = {329--333},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/QuLBQ22.bib},
  doi = {10.1109/ISCSLP57327.2022.10038203},
  timestamp = {Fri, 17 Feb 2023 18:27:20 +0100},
  url = {https://doi.org/10.1109/ISCSLP57327.2022.10038203}
}

Text-Informed Knowledge Distillation for Robust Speech Enhancement and Recognition

Wei Wang , Wangyou Zhang , Shaoxiong Lin , and Yanmin Qian

In 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022, Singapore, December 11-14, 2022 , Oct 2022

Bib

@inproceedings{Wang2022b,
  author = {Wang, Wei and Zhang, Wangyou and Lin, Shaoxiong and Qian, Yanmin},
  booktitle = {13th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2022, Singapore, December 11-14, 2022},
  title = {Text-Informed Knowledge Distillation for Robust Speech Enhancement and Recognition},
  year = {2022},
  editor = {Lee, Kong Aik and Lee, Hung{-}yi and Lu, Yanfeng and Dong, Minghui},
  pages = {334--338},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/WangZLQ22.bib},
  doi = {10.1109/ISCSLP57327.2022.10037802},
  timestamp = {Fri, 17 Feb 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ISCSLP57327.2022.10037802}
}

Medical Difficult Airway Detection using Speech Technology

Zhikai Zhou , Shuang Cao , Zhengyang Chen , Bei Liu , Ming Xia , Hong Jiang , and Yanmin Qian

In 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022, Singapore, December 11-14, 2022 , Oct 2022

Bib

@inproceedings{Zhou2022b,
  author = {Zhou, Zhikai and Cao, Shuang and Chen, Zhengyang and Liu, Bei and Xia, Ming and Jiang, Hong and Qian, Yanmin},
  booktitle = {13th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2022, Singapore, December 11-14, 2022},
  title = {Medical Difficult Airway Detection using Speech Technology},
  year = {2022},
  editor = {Lee, Kong Aik and Lee, Hung{-}yi and Lu, Yanfeng and Dong, Minghui},
  pages = {349--353},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/ZhouCCLXJQ22.bib},
  doi = {10.1109/ISCSLP57327.2022.10037911},
  timestamp = {Fri, 17 Feb 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ISCSLP57327.2022.10037911}
}

Speaking style compensation on synthetic audio for robust keyword spotting

Houjun Huang , and Yanmin Qian

In 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022, Singapore, December 11-14, 2022 , Oct 2022

Bib

@inproceedings{Huang2022,
  author = {Huang, Houjun and Qian, Yanmin},
  booktitle = {13th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2022, Singapore, December 11-14, 2022},
  title = {Speaking style compensation on synthetic audio for robust keyword spotting},
  year = {2022},
  editor = {Lee, Kong Aik and Lee, Hung{-}yi and Lu, Yanfeng and Dong, Minghui},
  pages = {448--452},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/HuangQ22.bib},
  doi = {10.1109/ISCSLP57327.2022.10038031},
  timestamp = {Mon, 13 Mar 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ISCSLP57327.2022.10038031}
}

The Conversational Short-phrase Speaker Diarization (CSSD) Task: Dataset, Evaluation Metric and Baselines

Gaofeng Cheng , Yifan Chen , Runyan Yang , Qingxuan Li , Zehui Yang , Lingxuan Ye , Pengyuan Zhang , Qingqing Zhang , Lei Xie , Yanmin Qian , Kong Aik Lee , and Yonghong Yan

In 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022, Singapore, December 11-14, 2022 , Oct 2022

Bib

@inproceedings{Cheng2022,
  author = {Cheng, Gaofeng and Chen, Yifan and Yang, Runyan and Li, Qingxuan and Yang, Zehui and Ye, Lingxuan and Zhang, Pengyuan and Zhang, Qingqing and Xie, Lei and Qian, Yanmin and Lee, Kong Aik and Yan, Yonghong},
  booktitle = {13th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2022, Singapore, December 11-14, 2022},
  title = {The Conversational Short-phrase Speaker Diarization {(CSSD)} Task: Dataset, Evaluation Metric and Baselines},
  year = {2022},
  editor = {Lee, Kong Aik and Lee, Hung{-}yi and Lu, Yanfeng and Dong, Minghui},
  pages = {488--492},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/ChengCYLYYZZXQLY22.bib},
  doi = {10.1109/ISCSLP57327.2022.10038258},
  timestamp = {Tue, 14 Mar 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ISCSLP57327.2022.10038258}
}

The X-Lance Speaker Diarization System for the Conversational Short-phrase Speaker Diarization Challenge 2022

Tao Liu , Xu Xiang , Zhengyang Chen , Bing Han , Kai Yu, and Yanmin Qian

In 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022, Singapore, December 11-14, 2022 , Oct 2022

Bib

@inproceedings{Liu2022e,
  author = {Liu, Tao and Xiang, Xu and Chen, Zhengyang and Han, Bing and Yu, Kai and Qian, Yanmin},
  booktitle = {13th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2022, Singapore, December 11-14, 2022},
  title = {The X-Lance Speaker Diarization System for the Conversational Short-phrase Speaker Diarization Challenge 2022},
  year = {2022},
  editor = {Lee, Kong Aik and Lee, Hung{-}yi and Lu, Yanfeng and Dong, Minghui},
  pages = {498--501},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/LiuXCHYQ22.bib},
  doi = {10.1109/ISCSLP57327.2022.10037955},
  timestamp = {Fri, 17 Feb 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ISCSLP57327.2022.10037955}
}

End-to-End Multi-Speaker ASR with Independent Vector Analysis

Robin Scheibler , Wangyou Zhang , Xuankai Chang , Shinji Watanabe , and Yanmin Qian

In IEEE Spoken Language Technology Workshop, SLT 2022, Doha, Qatar, January 9-12, 2023 , Oct 2022

Bib

@inproceedings{Scheibler2022,
  author = {Scheibler, Robin and Zhang, Wangyou and Chang, Xuankai and Watanabe, Shinji and Qian, Yanmin},
  booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2022, Doha, Qatar, January 9-12, 2023},
  title = {End-to-End Multi-Speaker {ASR} with Independent Vector Analysis},
  year = {2022},
  pages = {496--501},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/slt/ScheiblerZCWQ22.bib},
  doi = {10.1109/SLT54892.2023.10023037},
  timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/SLT54892.2023.10023037}
}

A Comprehensive Study on Self-Supervised Distillation for Speaker Representation Learning

Zhengyang Chen , Yao Qian , Bing Han , Yanmin Qian , and Michael Zeng

In IEEE Spoken Language Technology Workshop, SLT 2022, Doha, Qatar, January 9-12, 2023 , Oct 2022

Bib

@inproceedings{Chen2022c,
  author = {Chen, Zhengyang and Qian, Yao and Han, Bing and Qian, Yanmin and Zeng, Michael},
  booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2022, Doha, Qatar, January 9-12, 2023},
  title = {A Comprehensive Study on Self-Supervised Distillation for Speaker Representation Learning},
  year = {2022},
  pages = {599--604},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/slt/ChenQHQZ22.bib},
  doi = {10.1109/SLT54892.2023.10022470},
  timestamp = {Mon, 06 Feb 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/SLT54892.2023.10022470}
}

The SJTU X-LANCE Lab System for CNSRC 2022

Zhengyang Chen , Bei Liu , Bing Han , Leying Zhang , and Yanmin Qian

CoRR, Oct 2022

Bib

@article{Chen2022d,
  author = {Chen, Zhengyang and Liu, Bei and Han, Bing and Zhang, Leying and Qian, Yanmin},
  journal = {CoRR},
  title = {The {SJTU} {X-LANCE} Lab System for {CNSRC} 2022},
  year = {2022},
  volume = {abs/2206.11699},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2206-11699.bib},
  doi = {10.48550/ARXIV.2206.11699},
  eprint = {2206.11699},
  timestamp = {Mon, 27 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2206.11699}
}

SJTU-AISPEECH System for VoxCeleb Speaker Recognition Challenge 2022

Zhengyang Chen , Bing Han , Xu Xiang , Houjun Huang , Bei Liu , and Yanmin Qian

CoRR, Oct 2022

Bib

@article{Chen2022e,
  author = {Chen, Zhengyang and Han, Bing and Xiang, Xu and Huang, Houjun and Liu, Bei and Qian, Yanmin},
  journal = {CoRR},
  title = {{SJTU-AISPEECH} System for VoxCeleb Speaker Recognition Challenge 2022},
  year = {2022},
  volume = {abs/2209.09076},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2209-09076.bib},
  doi = {10.48550/ARXIV.2209.09076},
  eprint = {2209.09076},
  timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2209.09076}
}

Build a SRE Challenge System: Lessons from VoxSRC 2022 and CNSRC 2022

Zhengyang Chen , Bing Han , Xu Xiang , Houjun Huang , Bei Liu , and Yanmin Qian

CoRR, Oct 2022

Bib

@article{Chen2022g,
  author = {Chen, Zhengyang and Han, Bing and Xiang, Xu and Huang, Houjun and Liu, Bei and Qian, Yanmin},
  journal = {CoRR},
  title = {Build a {SRE} Challenge System: Lessons from VoxSRC 2022 and {CNSRC} 2022},
  year = {2022},
  volume = {abs/2211.00815},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2211-00815.bib},
  doi = {10.48550/ARXIV.2211.00815},
  eprint = {2211.00815},
  timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2211.00815}
}

Factorized Neural Transducer for Efficient Language Model Adaptation

Xie Chen, Zhong Meng , Sarangarajan Parthasarathy , and Jinyu Li

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Chen2022h,
  author = {Chen, Xie and Meng, Zhong and Parthasarathy, Sarangarajan and Li, Jinyu},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Factorized Neural Transducer for Efficient Language Model Adaptation},
  year = {2022},
  pages = {8132--8136},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ChenMPL22.bib},
  doi = {10.1109/ICASSP43922.2022.9746908},
  timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746908}
}

VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature

Chenpeng Du , Yiwei Guo , Xie Chen, and Kai Yu

In Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022 , Oct 2022

Bib

@inproceedings{Du2022,
  author = {Du, Chenpeng and Guo, Yiwei and Chen, Xie and Yu, Kai},
  booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022},
  title = {{VQTTS:} High-Fidelity Text-to-Speech Synthesis with Self-Supervised {VQ} Acoustic Feature},
  year = {2022},
  editor = {Ko, Hanseok and Hansen, John H. L.},
  pages = {1596--1600},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/DuGC022.bib},
  doi = {10.21437/INTERSPEECH.2022-489},
  timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2022-489}
}

Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition

Zhong Meng , Yashesh Gaur , Naoyuki Kanda , Jinyu Li , Xie Chen , Yu Wu , and Yifan Gong

In Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022 , Oct 2022

Bib

@inproceedings{Meng2022,
  author = {Meng, Zhong and Gaur, Yashesh and Kanda, Naoyuki and Li, Jinyu and Chen, Xie and Wu, Yu and Gong, Yifan},
  booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022},
  title = {Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition},
  year = {2022},
  editor = {Ko, Hanseok and Hansen, John H. L.},
  pages = {2608--2612},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/MengGK0CW022.bib},
  doi = {10.21437/INTERSPEECH.2022-13},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2022-13}
}

Exploring Effective Distillation of Self-Supervised Speech Models for Automatic Speech Recognition

Yujin Wang , Changli Tang , Ziyang Ma , Zhisheng Zheng , Xie Chen, and Wei-Qiang Zhang

CoRR, Oct 2022

Bib

@article{Wang2022d,
  author = {Wang, Yujin and Tang, Changli and Ma, Ziyang and Zheng, Zhisheng and Chen, Xie and Zhang, Wei{-}Qiang},
  journal = {CoRR},
  title = {Exploring Effective Distillation of Self-Supervised Speech Models for Automatic Speech Recognition},
  year = {2022},
  volume = {abs/2210.15631},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2210-15631.bib},
  doi = {10.48550/ARXIV.2210.15631},
  eprint = {2210.15631},
  timestamp = {Tue, 24 Jan 2023 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2210.15631}
}

MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets

Ziyang Ma , Zhisheng Zheng , Changli Tang , Yujin Wang , and Xie Chen

CoRR, Oct 2022

Bib

@article{Ma2022,
  author = {Ma, Ziyang and Zheng, Zhisheng and Tang, Changli and Wang, Yujin and Chen, Xie},
  journal = {CoRR},
  title = {{MT4SSL:} Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets},
  year = {2022},
  volume = {abs/2211.07321},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2211-07321.bib},
  doi = {10.48550/ARXIV.2211.07321},
  eprint = {2211.07321},
  timestamp = {Tue, 24 Jan 2023 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2211.07321}
}

EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance

Yiwei Guo , Chenpeng Du , Xie Chen, and Kai Yu

CoRR, Oct 2022

Bib

@article{Guo2022,
  author = {Guo, Yiwei and Du, Chenpeng and Chen, Xie and Yu, Kai},
  journal = {CoRR},
  title = {EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance},
  year = {2022},
  volume = {abs/2211.09496},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2211-09496.bib},
  doi = {10.48550/ARXIV.2211.09496},
  eprint = {2211.09496},
  timestamp = {Tue, 24 Jan 2023 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2211.09496}
}

Exploring Effective Fusion Algorithms for Speech Based Self-Supervised Learning Models

Changli Tang , Yujin Wang , Xie Chen, and Wei-Qiang Zhang

CoRR, Oct 2022

Bib

@article{Tang2022,
  author = {Tang, Changli and Wang, Yujin and Chen, Xie and Zhang, Wei{-}Qiang},
  journal = {CoRR},
  title = {Exploring Effective Fusion Algorithms for Speech Based Self-Supervised Learning Models},
  year = {2022},
  volume = {abs/2212.10092},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2212-10092.bib},
  doi = {10.48550/ARXIV.2212.10092},
  eprint = {2212.10092},
  timestamp = {Tue, 24 Jan 2023 00:00:00 +0100},
  url = {https://doi.org/10.48550/arXiv.2212.10092}
}

D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat

Binwei Yao , Chao Shi , Likai Zou , Lingfeng Dai , Mengyue Wu, Lu Chen, Zhen Wang , and Kai Yu

In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022 , Oct 2022

Bib

@inproceedings{Yao2022,
  author = {Yao, Binwei and Shi, Chao and Zou, Likai and Dai, Lingfeng and Wu, Mengyue and Chen, Lu and Wang, Zhen and Yu, Kai},
  booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, {EMNLP} 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022},
  title = {{D4:} a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat},
  year = {2022},
  editor = {Goldberg, Yoav and Kozareva, Zornitsa and Zhang, Yue},
  pages = {2438--2459},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/emnlp/YaoSZDWCWY22.bib},
  doi = {10.18653/V1/2022.EMNLP-MAIN.156},
  timestamp = {Thu, 10 Aug 2023 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/2022.emnlp-main.156}
}

Symptom Identification for Interpretable Detection of Multiple Mental Disorders on Social Media

Zhiling Zhang , Siyuan Chen , Mengyue Wu , and Kenny Q. Zhu

In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022 , Oct 2022

Bib

@inproceedings{Zhang2022c,
  author = {Zhang, Zhiling and Chen, Siyuan and Wu, Mengyue and Zhu, Kenny Q.},
  booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, {EMNLP} 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022},
  title = {Symptom Identification for Interpretable Detection of Multiple Mental Disorders on Social Media},
  year = {2022},
  editor = {Goldberg, Yoav and Kozareva, Zornitsa and Zhang, Yue},
  pages = {9970--9985},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/emnlp/ZhangCWZ22.bib},
  doi = {10.18653/V1/2022.EMNLP-MAIN.677},
  timestamp = {Thu, 10 Aug 2023 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/2022.emnlp-main.677}
}

Category-Adapted Sound Event Enhancement with Weakly Labeled Data

Guangwei Li , Xuenan Xu , Heinrich Dinkel , Mengyue Wu, and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Li2022c,
  author = {Li, Guangwei and Xu, Xuenan and Dinkel, Heinrich and Wu, Mengyue and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Category-Adapted Sound Event Enhancement with Weakly Labeled Data},
  year = {2022},
  pages = {851--855},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/LiXDWY22.bib},
  doi = {10.1109/ICASSP43922.2022.9747722},
  timestamp = {Tue, 07 Jun 2022 17:34:47 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9747722}
}

Diversity-Controllable and Accurate Audio Captioning Based on Neural Condition

Xuenan Xu , Mengyue Wu, and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Xu2022,
  author = {Xu, Xuenan and Wu, Mengyue and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Diversity-Controllable and Accurate Audio Captioning Based on Neural Condition},
  year = {2022},
  pages = {971--975},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/XuWY22.bib},
  doi = {10.1109/ICASSP43922.2022.9746834},
  timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746834}
}

Can Audio Captions Be Evaluated With Image Caption Metrics?

Zelin Zhou , Zhiling Zhang , Xuenan Xu , Zeyu Xie , Mengyue Wu , and Kenny Q. Zhu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Zhou2022c,
  author = {Zhou, Zelin and Zhang, Zhiling and Xu, Xuenan and Xie, Zeyu and Wu, Mengyue and Zhu, Kenny Q.},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Can Audio Captions Be Evaluated With Image Caption Metrics?},
  year = {2022},
  pages = {981--985},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ZhouZXXWZ22.bib},
  doi = {10.1109/ICASSP43922.2022.9746427},
  timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746427}
}

Navigating Audio-Visual Event Detection Across Mismatched Modalities

Guangwei Li , Xuenan Xu , Mengyue Wu, and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Li2022d,
  author = {Li, Guangwei and Xu, Xuenan and Wu, Mengyue and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Navigating Audio-Visual Event Detection Across Mismatched Modalities},
  year = {2022},
  pages = {1975--1979},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/LiXWY22.bib},
  doi = {10.1109/ICASSP43922.2022.9747579},
  timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9747579}
}

Audio-Text Retrieval in Context

Siyu Lou , Xuenan Xu , Mengyue Wu, and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Lou2022,
  author = {Lou, Siyu and Xu, Xuenan and Wu, Mengyue and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Audio-Text Retrieval in Context},
  year = {2022},
  pages = {4793--4797},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/LouXWY22.bib},
  doi = {10.1109/ICASSP43922.2022.9746786},
  timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746786}
}

Climate and Weather: Inspecting Depression Detection via Emotion Recognition

Wen Wu , Mengyue Wu, and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Wu2022a,
  author = {Wu, Wen and Wu, Mengyue and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Climate and Weather: Inspecting Depression Detection via Emotion Recognition},
  year = {2022},
  pages = {6262--6266},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/WuWY22.bib},
  doi = {10.1109/ICASSP43922.2022.9746634},
  timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746634}
}

Psychiatric Scale Guided Risky Post Screening for Early Detection of Depression

Zhiling Zhang , Siyuan Chen , Mengyue Wu , and Kenny Q. Zhu

In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23-29 July 2022 , Oct 2022

Bib

@inproceedings{Zhang2022d,
  author = {Zhang, Zhiling and Chen, Siyuan and Wu, Mengyue and Zhu, Kenny Q.},
  booktitle = {Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, {IJCAI} 2022, Vienna, Austria, 23-29 July 2022},
  title = {Psychiatric Scale Guided Risky Post Screening for Early Detection of Depression},
  year = {2022},
  editor = {Raedt, Luc De},
  pages = {5220--5226},
  publisher = {ijcai.org},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/ijcai/ZhangCWZ22.bib},
  doi = {10.24963/IJCAI.2022/725},
  timestamp = {Wed, 27 Jul 2022 16:43:00 +0200},
  url = {https://doi.org/10.24963/ijcai.2022/725}
}

A Comprehensive Survey of Automated Audio Captioning

Xuenan Xu , Mengyue Wu, and Kai Yu

CoRR, Oct 2022

Bib

@article{Xu2022a,
  author = {Xu, Xuenan and Wu, Mengyue and Yu, Kai},
  journal = {CoRR},
  title = {A Comprehensive Survey of Automated Audio Captioning},
  year = {2022},
  volume = {abs/2205.05357},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2205-05357.bib},
  doi = {10.48550/ARXIV.2205.05357},
  eprint = {2205.05357},
  timestamp = {Tue, 17 May 2022 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2205.05357}
}

DialogZoo: Large-Scale Dialog-Oriented Task Learning

Zhi Chen , Jijia Bao , Lu Chen, Yuncong Liu , Da Ma , Bei Chen , Mengyue Wu , Su Zhu , Jian-Guang Lou , and Kai Yu

CoRR, Oct 2022

Bib

@article{Chen2022i,
  author = {Chen, Zhi and Bao, Jijia and Chen, Lu and Liu, Yuncong and Ma, Da and Chen, Bei and Wu, Mengyue and Zhu, Su and Lou, Jian{-}Guang and Yu, Kai},
  journal = {CoRR},
  title = {DialogZoo: Large-Scale Dialog-Oriented Task Learning},
  year = {2022},
  volume = {abs/2205.12662},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2205-12662.bib},
  doi = {10.48550/ARXIV.2205.12662},
  eprint = {2205.12662},
  timestamp = {Mon, 30 May 2022 01:00:00 +0200},
  url = {https://doi.org/10.48550/arXiv.2205.12662}
}

Data augmentation based non-parallel voice conversion with frame-level speaker disentangler

Bo Chen , Zhihang Xu , and Kai Yu

Speech Commun., Oct 2022

Bib

@article{Chen2022k,
  author = {Chen, Bo and Xu, Zhihang and Yu, Kai},
  journal = {Speech Commun.},
  title = {Data augmentation based non-parallel voice conversion with frame-level speaker disentangler},
  year = {2022},
  pages = {14--22},
  volume = {136},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/speech/ChenXY22.bib},
  doi = {10.1016/J.SPECOM.2021.10.001},
  timestamp = {Fri, 21 Jan 2022 00:00:00 +0100},
  url = {https://doi.org/10.1016/j.specom.2021.10.001}
}

Phone-Level Prosody Modelling With GMM-Based MDN for Diverse and Controllable Speech Synthesis

Chenpeng Du , and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2022

Bib

@article{Du2022b,
  author = {Du, Chenpeng and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Phone-Level Prosody Modelling With GMM-Based {MDN} for Diverse and Controllable Speech Synthesis},
  year = {2022},
  pages = {190--201},
  volume = {30},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/DuY22.bib},
  doi = {10.1109/TASLP.2021.3133205},
  timestamp = {Tue, 08 Feb 2022 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2021.3133205}
}

Neural Fusion for Voice Cloning

Bo Chen , Chenpeng Du , and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2022

Bib

@article{Chen2022l,
  author = {Chen, Bo and Du, Chenpeng and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Neural Fusion for Voice Cloning},
  year = {2022},
  pages = {1993--2001},
  volume = {30},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/ChenDY22.bib},
  doi = {10.1109/TASLP.2022.3171971},
  timestamp = {Tue, 28 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/TASLP.2022.3171971}
}

META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI

Liangtai Sun , Xingyu Chen , Lu Chen, Tianle Dai , Zichen Zhu, and Kai Yu

In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022 , Oct 2022

Bib

@inproceedings{Sun2022,
  author = {Sun, Liangtai and Chen, Xingyu and Chen, Lu and Dai, Tianle and Zhu, Zichen and Yu, Kai},
  booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, {EMNLP} 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022},
  title = {{META-GUI:} Towards Multi-modal Conversational Agents on Mobile {GUI}},
  year = {2022},
  editor = {Goldberg, Yoav and Kozareva, Zornitsa and Zhang, Yue},
  pages = {6699--6712},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/emnlp/SunCCDZY22.bib},
  doi = {10.18653/V1/2022.EMNLP-MAIN.449},
  timestamp = {Thu, 10 Aug 2023 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/2022.emnlp-main.449}
}

AdapterShare: Task Correlation Modeling with Adapter Differentiation

Zhi Chen , Bei Chen , Lu Chen, Kai Yu, and Jian-Guang Lou

In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022 , Oct 2022

Bib

@inproceedings{Chen2022m,
  author = {Chen, Zhi and Chen, Bei and Chen, Lu and Yu, Kai and Lou, Jian{-}Guang},
  booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, {EMNLP} 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022},
  title = {AdapterShare: Task Correlation Modeling with Adapter Differentiation},
  year = {2022},
  editor = {Goldberg, Yoav and Kozareva, Zornitsa and Zhang, Yue},
  pages = {10645--10651},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/emnlp/ChenC00L22.bib},
  doi = {10.18653/V1/2022.EMNLP-MAIN.728},
  timestamp = {Thu, 10 Aug 2023 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/2022.emnlp-main.728}
}

LatticeBART: Lattice-to-Lattice Pre-Training for Speech Recognition

Lingfeng Dai , Lu Chen, Zhikai Zhou , and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Dai2022,
  author = {Dai, Lingfeng and Chen, Lu and Zhou, Zhikai and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {LatticeBART: Lattice-to-Lattice Pre-Training for Speech Recognition},
  year = {2022},
  pages = {6112--6116},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/DaiCZY22.bib},
  doi = {10.1109/ICASSP43922.2022.9746796},
  timestamp = {Sat, 29 Apr 2023 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746796}
}

Text Adaptive Detection for Customizable Keyword Spotting

Yu Xi , Tian Tan , Wangyou Zhang , Baochen Yang , and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Xi2022,
  author = {Xi, Yu and Tan, Tian and Zhang, Wangyou and Yang, Baochen and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Text Adaptive Detection for Customizable Keyword Spotting},
  year = {2022},
  pages = {6652--6656},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/XiTZYY22.bib},
  doi = {10.1109/ICASSP43922.2022.9746647},
  timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746647}
}

Unsupervised Word-Level Prosody Tagging for Controllable Speech Synthesis

Yiwei Guo , Chenpeng Du , and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022 , Oct 2022

Bib

@inproceedings{Guo2022a,
  author = {Guo, Yiwei and Du, Chenpeng and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  title = {Unsupervised Word-Level Prosody Tagging for Controllable Speech Synthesis},
  year = {2022},
  pages = {7597--7601},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/GuoDY22.bib},
  doi = {10.1109/ICASSP43922.2022.9746323},
  timestamp = {Thu, 23 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9746323}
}

The AISP-SJTU Simultaneous Translation System for IWSLT 2022

Qinpei Zhu , Renshou Wu , Guangfeng Liu , Xinyu Zhu , Xingyu Chen , Yang Zhou , Qingliang Miao , Rui Wang , and Kai Yu

In Proceedings of the 19th International Conference on Spoken Language Translation, IWSLT@ACL 2022, Dublin, Ireland (in-person and online), May 26-27, 2022 , Oct 2022

Bib

@inproceedings{Zhu2022,
  author = {Zhu, Qinpei and Wu, Renshou and Liu, Guangfeng and Zhu, Xinyu and Chen, Xingyu and Zhou, Yang and Miao, Qingliang and Wang, Rui and Yu, Kai},
  booktitle = {Proceedings of the 19th International Conference on Spoken Language Translation, IWSLT@ACL 2022, Dublin, Ireland (in-person and online), May 26-27, 2022},
  title = {The {AISP-SJTU} Simultaneous Translation System for {IWSLT} 2022},
  year = {2022},
  editor = {Salesky, Elizabeth and Federico, Marcello and Costa{-}juss{\`{a}}, Marta Ruiz},
  pages = {208--215},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iwslt/ZhuWLZCZMWY22.bib},
  doi = {10.18653/V1/2022.IWSLT-1.16},
  timestamp = {Wed, 12 Oct 2022 08:58:55 +0200},
  url = {https://doi.org/10.18653/v1/2022.iwslt-1.16}
}

TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages

Zihan Zhao , Lu Chen, Ruisheng Cao , Hongshen Xu , Xingyu Chen , and Kai Yu

In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022, Seattle, WA, United States, July 10-15, 2022 , Oct 2022

Bib

@inproceedings{Zhao2022,
  author = {Zhao, Zihan and Chen, Lu and Cao, Ruisheng and Xu, Hongshen and Chen, Xingyu and Yu, Kai},
  booktitle = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, {NAACL} 2022, Seattle, WA, United States, July 10-15, 2022},
  title = {{TIE:} Topological Information Enhanced Structural Reading Comprehension on Web Pages},
  year = {2022},
  editor = {Carpuat, Marine and de Marneffe, Marie{-}Catherine and Ru{\'{\i}}z, Iv{\'{a}}n Vladimir Meza},
  pages = {1808--1821},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/naacl/ZhaoCCXC022.bib},
  doi = {10.18653/V1/2022.NAACL-MAIN.132},
  timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/2022.naacl-main.132}
}

UniDU: Towards A Unified Generative Dialogue Understanding Framework

Zhi Chen , Lu Chen , Bei Chen , Libo Qin , Yuncong Liu , Su Zhu , Jian-Guang Lou , and Kai Yu

In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2022, Edinburgh, UK, 07-09 September 2022 , Oct 2022

Bib

@inproceedings{Chen2022n,
  author = {Chen, Zhi and Chen, Lu and Chen, Bei and Qin, Libo and Liu, Yuncong and Zhu, Su and Lou, Jian{-}Guang and Yu, Kai},
  booktitle = {Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, {SIGDIAL} 2022, Edinburgh, UK, 07-09 September 2022},
  title = {UniDU: Towards {A} Unified Generative Dialogue Understanding Framework},
  year = {2022},
  editor = {Lemon, Oliver and Hakkani{-}T{\"{u}}r, Dilek and Li, Junyi Jessy and Ashrafzadeh, Arash and Garc{\'{\i}}a, Daniel Hern{\'{a}}ndez and Alikhani, Malihe and Vandyke, David and Dusek, Ondrej},
  pages = {442--455},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/sigdial/ChenCCQLZL022.bib},
  timestamp = {Thu, 19 Jan 2023 00:00:00 +0100},
  url = {https://aclanthology.org/2022.sigdial-1.43}
}

The AISP-SJTU Translation System for WMT 2022

Guangfeng Liu , Qinpei Zhu , Xingyu Chen , Renjie Feng , Jianxin Ren , Renshou Wu , Qingliang Miao , Rui Wang , and Kai Yu

In Proceedings of the Seventh Conference on Machine Translation, WMT 2022, Abu Dhabi, United Arab Emirates (Hybrid), December 7-8, 2022 , Oct 2022

Bib

@inproceedings{Liu2022f,
  author = {Liu, Guangfeng and Zhu, Qinpei and Chen, Xingyu and Feng, Renjie and Ren, Jianxin and Wu, Renshou and Miao, Qingliang and Wang, Rui and Yu, Kai},
  booktitle = {Proceedings of the Seventh Conference on Machine Translation, {WMT} 2022, Abu Dhabi, United Arab Emirates (Hybrid), December 7-8, 2022},
  title = {The {AISP-SJTU} Translation System for {WMT} 2022},
  year = {2022},
  editor = {Koehn, Philipp and Barrault, Lo{\"{\i}}c and Bojar, Ondrej and Bougares, Fethi and Chatterjee, Rajen and Costa{-}juss{\`{a}}, Marta R. and Federmann, Christian and Fishel, Mark and Fraser, Alexander and Freitag, Markus and Graham, Yvette and Grundkiewicz, Roman and Guzman, Paco and Haddow, Barry and Huck, Matthias and Jimeno{-}Yepes, Antonio and Kocmi, Tom and Martins, Andr{\'{e}} and Morishita, Makoto and Monz, Christof and Nagata, Masaaki and Nakazawa, Toshiaki and Negri, Matteo and N{\'{e}}v{\'{e}}ol, Aur{\'{e}}lie and Neves, Mariana and Popel, Martin and Turchi, Marco and Zampieri, Marcos},
  pages = {310--317},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/wmt/LiuZCFRWMWY22.bib},
  timestamp = {Fri, 17 Mar 2023 17:00:14 +0100},
  url = {https://aclanthology.org/2022.wmt-1.24}
}

2021

Modified Magnitude-Phase Spectrum Information for Spoofing Detection

Jichen Yang , Hongji Wang , Rohan Kumar Das , and Yanmin Qian

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2021

Bib

@article{Yang2021,
  author = {Yang, Jichen and Wang, Hongji and Das, Rohan Kumar and Qian, Yanmin},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Modified Magnitude-Phase Spectrum Information for Spoofing Detection},
  year = {2021},
  pages = {1065--1078},
  volume = {29},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/YangWDQ21.bib},
  doi = {10.1109/TASLP.2021.3060810},
  timestamp = {Tue, 23 Mar 2021 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2021.3060810}
}

Audio-Visual Deep Neural Network for Robust Person Verification

Yanmin Qian , Zhengyang Chen , and Shuai Wang

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2021

Bib

@article{Qian2021,
  author = {Qian, Yanmin and Chen, Zhengyang and Wang, Shuai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Audio-Visual Deep Neural Network for Robust Person Verification},
  year = {2021},
  pages = {1079--1092},
  volume = {29},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/QianCW21.bib},
  doi = {10.1109/TASLP.2021.3057230},
  timestamp = {Thu, 29 Apr 2021 01:00:00 +0200},
  url = {https://doi.org/10.1109/TASLP.2021.3057230}
}

Dual-Path Modeling for Long Recording Speech Separation in Meetings

Chenda Li , Zhuo Chen , Yi Luo , Cong Han , Tianyan Zhou , Keisuke Kinoshita , Marc Delcroix , Shinji Watanabe , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021 , Oct 2021

Bib

@inproceedings{Li2021,
  author = {Li, Chenda and Chen, Zhuo and Luo, Yi and Han, Cong and Zhou, Tianyan and Kinoshita, Keisuke and Delcroix, Marc and Watanabe, Shinji and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  title = {Dual-Path Modeling for Long Recording Speech Separation in Meetings},
  year = {2021},
  pages = {5739--5743},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/LiCLHZKD0Q21.bib},
  doi = {10.1109/ICASSP39728.2021.9414127},
  timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP39728.2021.9414127}
}

Self-Supervised Learning Based Domain Adaptation for Robust Speaker Verification

Zhengyang Chen , Shuai Wang , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021 , Oct 2021

Bib

@inproceedings{Chen2021,
  author = {Chen, Zhengyang and Wang, Shuai and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  title = {Self-Supervised Learning Based Domain Adaptation for Robust Speaker Verification},
  year = {2021},
  pages = {5834--5838},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ChenWQ21.bib},
  doi = {10.1109/ICASSP39728.2021.9414261},
  timestamp = {Fri, 10 Mar 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP39728.2021.9414261}
}

SynAug: Synthesis-Based Data Augmentation for Text-Dependent Speaker Verification

Chenpeng Du , Bing Han , Shuai Wang , Yanmin Qian , and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021 , Oct 2021

Bib

@inproceedings{Du2021,
  author = {Du, Chenpeng and Han, Bing and Wang, Shuai and Qian, Yanmin and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  title = {SynAug: Synthesis-Based Data Augmentation for Text-Dependent Speaker Verification},
  year = {2021},
  pages = {5844--5848},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/DuHWQ021.bib},
  doi = {10.1109/ICASSP39728.2021.9414438},
  timestamp = {Tue, 14 Dec 2021 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP39728.2021.9414438}
}

Unit Selection Synthesis Based Data Augmentation for Fixed Phrase Speaker Verification

Houjun Huang , Xu Xiang , Fei Zhao , Shuai Wang , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021 , Oct 2021

Bib

@inproceedings{Huang2021,
  author = {Huang, Houjun and Xiang, Xu and Zhao, Fei and Wang, Shuai and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  title = {Unit Selection Synthesis Based Data Augmentation for Fixed Phrase Speaker Verification},
  year = {2021},
  pages = {5849--5853},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/HuangXZWQ21.bib},
  doi = {10.1109/ICASSP39728.2021.9414550},
  timestamp = {Fri, 10 Mar 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP39728.2021.9414550}
}

AISpeech-SJTU Accent Identification System for the Accented English Speech Recognition Challenge

Houjun Huang , Xu Xiang , Yexin Yang , Rao Ma , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021 , Oct 2021

Bib

@inproceedings{Huang2021a,
  author = {Huang, Houjun and Xiang, Xu and Yang, Yexin and Ma, Rao and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  title = {AISpeech-SJTU Accent Identification System for the Accented English Speech Recognition Challenge},
  year = {2021},
  pages = {6254--6258},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/HuangXYMQ21.bib},
  doi = {10.1109/ICASSP39728.2021.9414292},
  timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP39728.2021.9414292}
}

AISpeech-SJTU ASR System for the Accented English Speech Recognition Challenge

Tian Tan , Yizhou Lu , Rao Ma , Sen Zhu , Jiaqi Guo , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021 , Oct 2021

Bib

@inproceedings{Tan2021,
  author = {Tan, Tian and Lu, Yizhou and Ma, Rao and Zhu, Sen and Guo, Jiaqi and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  title = {AISpeech-SJTU {ASR} System for the Accented English Speech Recognition Challenge},
  year = {2021},
  pages = {6413--6417},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/0002LMZGQ21.bib},
  doi = {10.1109/ICASSP39728.2021.9414471},
  timestamp = {Fri, 09 Jul 2021 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP39728.2021.9414471}
}

Towards Data Selection on TTS Data for Children’s Speech Recognition

Wei Wang , Zhikai Zhou , Yizhou Lu , Hongji Wang , Chenpeng Du , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021 , Oct 2021

Bib

@inproceedings{Wang2021,
  author = {Wang, Wei and Zhou, Zhikai and Lu, Yizhou and Wang, Hongji and Du, Chenpeng and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  title = {Towards Data Selection on {TTS} Data for Children's Speech Recognition},
  year = {2021},
  pages = {6888--6892},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/WangZLWDQ21.bib},
  doi = {10.1109/ICASSP39728.2021.9413930},
  timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP39728.2021.9413930}
}

End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend

Wangyou Zhang , Christoph Böddeker , Shinji Watanabe , Tomohiro Nakatani , Marc Delcroix , Keisuke Kinoshita , Tsubasa Ochiai , Naoyuki Kamo , Reinhold Haeb-Umbach , and Yanmin Qian

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021 , Oct 2021

Bib

@inproceedings{Zhang2021,
  author = {Zhang, Wangyou and B{\"{o}}ddeker, Christoph and Watanabe, Shinji and Nakatani, Tomohiro and Delcroix, Marc and Kinoshita, Keisuke and Ochiai, Tsubasa and Kamo, Naoyuki and Haeb{-}Umbach, Reinhold and Qian, Yanmin},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  title = {End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend},
  year = {2021},
  pages = {6898--6902},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ZhangB0NDKOKHQ21.bib},
  doi = {10.1109/ICASSP39728.2021.9414464},
  timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP39728.2021.9414464}
}

The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods

Xian Shi , Fan Yu , Yizhou Lu , Yuhao Liang , Qiangze Feng , Daliang Wang , Yanmin Qian , and Lei Xie

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021 , Oct 2021

Bib

@inproceedings{Shi2021,
  author = {Shi, Xian and Yu, Fan and Lu, Yizhou and Liang, Yuhao and Feng, Qiangze and Wang, Daliang and Qian, Yanmin and Xie, Lei},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  title = {The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods},
  year = {2021},
  pages = {6918--6922},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ShiYLLFWQX21.bib},
  doi = {10.1109/ICASSP39728.2021.9413386},
  timestamp = {Mon, 31 Oct 2022 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP39728.2021.9413386}
}

Convolutive Transfer Function Invariant SDR Training Criteria for Multi-Channel Reverberant Speech Separation

Christoph Böddeker , Wangyou Zhang , Tomohiro Nakatani , Keisuke Kinoshita , Tsubasa Ochiai , Marc Delcroix , Naoyuki Kamo , Yanmin Qian , and Reinhold Haeb-Umbach

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021 , Oct 2021

Bib

@inproceedings{Boeddeker2021,
  author = {B{\"{o}}ddeker, Christoph and Zhang, Wangyou and Nakatani, Tomohiro and Kinoshita, Keisuke and Ochiai, Tsubasa and Delcroix, Marc and Kamo, Naoyuki and Qian, Yanmin and Haeb{-}Umbach, Reinhold},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  title = {Convolutive Transfer Function Invariant {SDR} Training Criteria for Multi-Channel Reverberant Speech Separation},
  year = {2021},
  pages = {8428--8432},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/BoddekerZNKODKQ21.bib},
  doi = {10.1109/ICASSP39728.2021.9414661},
  timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP39728.2021.9414661}
}

Layer-Wise Fast Adaptation for End-to-End Multi-Accent Speech Recognition

Xun Gong , Yizhou Lu , Zhikai Zhou , and Yanmin Qian

In Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021 , Oct 2021

Bib

@inproceedings{Gong2021,
  author = {Gong, Xun and Lu, Yizhou and Zhou, Zhikai and Qian, Yanmin},
  booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021},
  title = {Layer-Wise Fast Adaptation for End-to-End Multi-Accent Speech Recognition},
  year = {2021},
  editor = {Hermansky, Hynek and Cernock{\'{y}}, Honza and Burget, Luk{\'{a}}s and Lamel, Lori and Scharenborg, Odette and Motl{\'{\i}}cek, Petr},
  pages = {1274--1278},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/GongLZQ21.bib},
  doi = {10.21437/INTERSPEECH.2021-1075},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2021-1075}
}

Knowledge Distillation from Multi-Modality to Single-Modality for Person Verification

Leying Zhang , Zhengyang Chen , and Yanmin Qian

In Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021 , Oct 2021

Bib

@inproceedings{Zhang2021a,
  author = {Zhang, Leying and Chen, Zhengyang and Qian, Yanmin},
  booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021},
  title = {Knowledge Distillation from Multi-Modality to Single-Modality for Person Verification},
  year = {2021},
  editor = {Hermansky, Hynek and Cernock{\'{y}}, Honza and Burget, Luk{\'{a}}s and Lamel, Lori and Scharenborg, Odette and Motl{\'{\i}}cek, Petr},
  pages = {1897--1901},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ZhangCQ21.bib},
  doi = {10.21437/INTERSPEECH.2021-2119},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2021-2119}
}

Basis-MelGAN: Efficient Neural Vocoder Based on Audio Decomposition

Zhengxi Liu , and Yanmin Qian

In Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021 , Oct 2021

Bib

@inproceedings{Liu2021,
  author = {Liu, Zhengxi and Qian, Yanmin},
  booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021},
  title = {Basis-MelGAN: Efficient Neural Vocoder Based on Audio Decomposition},
  year = {2021},
  editor = {Hermansky, Hynek and Cernock{\'{y}}, Honza and Burget, Luk{\'{a}}s and Lamel, Lori and Scharenborg, Odette and Motl{\'{\i}}cek, Petr},
  pages = {2222--2226},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/LiuQ21.bib},
  doi = {10.21437/INTERSPEECH.2021-2173},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2021-2173}
}

The SJTU System for Short-Duration Speaker Verification Challenge 2021

Bing Han , Zhengyang Chen , Zhikai Zhou , and Yanmin Qian

In Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021 , Oct 2021

Bib

@inproceedings{Han2021,
  author = {Han, Bing and Chen, Zhengyang and Zhou, Zhikai and Qian, Yanmin},
  booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021},
  title = {The {SJTU} System for Short-Duration Speaker Verification Challenge 2021},
  year = {2021},
  editor = {Hermansky, Hynek and Cernock{\'{y}}, Honza and Burget, Luk{\'{a}}s and Lamel, Lori and Scharenborg, Odette and Motl{\'{\i}}cek, Petr},
  pages = {2332--2336},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/HanCZQ21.bib},
  doi = {10.21437/INTERSPEECH.2021-2136},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2021-2136}
}

Audio-Visual Multi-Talker Speech Recognition in a Cocktail Party

Yifei Wu , Chenda Li , Song Yang , Zhongqin Wu , and Yanmin Qian

In Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021 , Oct 2021

Bib

@inproceedings{Wu2021,
  author = {Wu, Yifei and Li, Chenda and Yang, Song and Wu, Zhongqin and Qian, Yanmin},
  booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021},
  title = {Audio-Visual Multi-Talker Speech Recognition in a Cocktail Party},
  year = {2021},
  editor = {Hermansky, Hynek and Cernock{\'{y}}, Honza and Burget, Luk{\'{a}}s and Lamel, Lori and Scharenborg, Odette and Motl{\'{\i}}cek, Petr},
  pages = {3021--3025},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/WuLYWQ21.bib},
  doi = {10.21437/INTERSPEECH.2021-2128},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2021-2128}
}

Speaker Embedding Augmentation with Noise Distribution Matching

Xun Gong , Zhengyang Chen , Yexin Yang , Shuai Wang , Lan Wang , and Yanmin Qian

In 12th International Symposium on Chinese Spoken Language Processing, ISCSLP 2021, Hong Kong, January 24-27, 2021 , Oct 2021

Bib

@inproceedings{Gong2021a,
  author = {Gong, Xun and Chen, Zhengyang and Yang, Yexin and Wang, Shuai and Wang, Lan and Qian, Yanmin},
  booktitle = {12th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2021, Hong Kong, January 24-27, 2021},
  title = {Speaker Embedding Augmentation with Noise Distribution Matching},
  year = {2021},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/GongCYWWQ21.bib},
  doi = {10.1109/ISCSLP49672.2021.9362090},
  timestamp = {Fri, 10 Mar 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ISCSLP49672.2021.9362090}
}

Revisiting the Statistics Pooling Layer in Deep Speaker Embedding Learning

Shuai Wang , Yexin Yang , Yanmin Qian , and Kai Yu

In 12th International Symposium on Chinese Spoken Language Processing, ISCSLP 2021, Hong Kong, January 24-27, 2021 , Oct 2021

Bib

@inproceedings{Wang2021a,
  author = {Wang, Shuai and Yang, Yexin and Qian, Yanmin and Yu, Kai},
  booktitle = {12th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2021, Hong Kong, January 24-27, 2021},
  title = {Revisiting the Statistics Pooling Layer in Deep Speaker Embedding Learning},
  year = {2021},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/WangYQ021.bib},
  doi = {10.1109/ISCSLP49672.2021.9362097},
  timestamp = {Tue, 14 Dec 2021 00:00:00 +0100},
  url = {https://doi.org/10.1109/ISCSLP49672.2021.9362097}
}

Data Augmentation for end-to-end Code-Switching Speech Recognition

Chenpeng Du , Hao Li , Yizhou Lu , Lan Wang , and Yanmin Qian

In IEEE Spoken Language Technology Workshop, SLT 2021, Shenzhen, China, January 19-22, 2021 , Oct 2021

Bib

@inproceedings{Du2021a,
  author = {Du, Chenpeng and Li, Hao and Lu, Yizhou and Wang, Lan and Qian, Yanmin},
  booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021},
  title = {Data Augmentation for end-to-end Code-Switching Speech Recognition},
  year = {2021},
  pages = {194--200},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/slt/DuLLWQ21.bib},
  doi = {10.1109/SLT48900.2021.9383620},
  timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
  url = {https://doi.org/10.1109/SLT48900.2021.9383620}
}

Dual-Path RNN for Long Recording Speech Separation

Chenda Li , Yi Luo , Cong Han , Jinyu Li , Takuya Yoshioka , Tianyan Zhou , Marc Delcroix , Keisuke Kinoshita , Christoph Böddeker , Yanmin Qian , Shinji Watanabe , and Zhuo Chen

In IEEE Spoken Language Technology Workshop, SLT 2021, Shenzhen, China, January 19-22, 2021 , Oct 2021

Bib

@inproceedings{Li2021a,
  author = {Li, Chenda and Luo, Yi and Han, Cong and Li, Jinyu and Yoshioka, Takuya and Zhou, Tianyan and Delcroix, Marc and Kinoshita, Keisuke and B{\"{o}}ddeker, Christoph and Qian, Yanmin and Watanabe, Shinji and Chen, Zhuo},
  booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021},
  title = {Dual-Path {RNN} for Long Recording Speech Separation},
  year = {2021},
  pages = {865--872},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/slt/LiLHLYZDKBQ0C21.bib},
  doi = {10.1109/SLT48900.2021.9383514},
  timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/SLT48900.2021.9383514}
}

Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions

Wangyou Zhang , Jing Shi , Chenda Li , Shinji Watanabe , and Yanmin Qian

In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021, New Paltz, NY, USA, October 17-20, 2021 , Oct 2021

Bib

@inproceedings{Zhang2021b,
  author = {Zhang, Wangyou and Shi, Jing and Li, Chenda and Watanabe, Shinji and Qian, Yanmin},
  booktitle = {{IEEE} Workshop on Applications of Signal Processing to Audio and Acoustics, {WASPAA} 2021, New Paltz, NY, USA, October 17-20, 2021},
  title = {Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions},
  year = {2021},
  pages = {146--150},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/waspaa/ZhangSLWQ21.bib},
  doi = {10.1109/WASPAA52581.2021.9632720},
  timestamp = {Thu, 23 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/WASPAA52581.2021.9632720}
}

Towards Duration Robust Weakly Supervised Sound Event Detection

Heinrich Dinkel , Mengyue Wu, and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2021

Bib

@article{Dinkel2021,
  author = {Dinkel, Heinrich and Wu, Mengyue and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Towards Duration Robust Weakly Supervised Sound Event Detection},
  year = {2021},
  pages = {887--900},
  volume = {29},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/DinkelW021.bib},
  doi = {10.1109/TASLP.2021.3054313},
  timestamp = {Tue, 23 Mar 2021 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2021.3054313}
}

Voice Activity Detection in the Wild: A Data-Driven Approach Using Teacher-Student Training

Heinrich Dinkel , Shuai Wang , Xuenan Xu , Mengyue Wu, and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2021

Bib

@article{Dinkel2021a,
  author = {Dinkel, Heinrich and Wang, Shuai and Xu, Xuenan and Wu, Mengyue and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Voice Activity Detection in the Wild: {A} Data-Driven Approach Using Teacher-Student Training},
  year = {2021},
  pages = {1542--1555},
  volume = {29},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/DinkelWXWY21.bib},
  doi = {10.1109/TASLP.2021.3073596},
  timestamp = {Tue, 15 Jun 2021 01:00:00 +0200},
  url = {https://doi.org/10.1109/TASLP.2021.3073596}
}

Building Interpretable Interaction Trees for Deep NLP Models

Die Zhang , Hao Zhang , Huilin Zhou , Xiaoyi Bao , Da Huo , Ruizhao Chen , Xu Cheng , Mengyue Wu, and Quanshi Zhang

In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021 , Oct 2021

Bib

@inproceedings{Zhang2021f,
  author = {Zhang, Die and Zhang, Hao and Zhou, Huilin and Bao, Xiaoyi and Huo, Da and Chen, Ruizhao and Cheng, Xu and Wu, Mengyue and Zhang, Quanshi},
  booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI} 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9, 2021},
  title = {Building Interpretable Interaction Trees for Deep {NLP} Models},
  year = {2021},
  pages = {14328--14337},
  publisher = {{AAAI} Press},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/aaai/ZhangZZBHCCWZ21.bib},
  doi = {10.1609/AAAI.V35I16.17685},
  timestamp = {Sat, 21 Oct 2023 01:00:00 +0200},
  url = {https://doi.org/10.1609/aaai.v35i16.17685}
}

Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL

Zhi Chen , Lu Chen, Hanqi Li , Ruisheng Cao , Da Ma , Mengyue Wu, and Kai Yu

In Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, Online Event, August 1-6, 2021 , Oct 2021

Bib

@inproceedings{Chen2021d,
  author = {Chen, Zhi and Chen, Lu and Li, Hanqi and Cao, Ruisheng and Ma, Da and Wu, Mengyue and Yu, Kai},
  booktitle = {Findings of the Association for Computational Linguistics: {ACL/IJCNLP} 2021, Online Event, August 1-6, 2021},
  title = {Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL},
  year = {2021},
  editor = {Zong, Chengqing and Xia, Fei and Li, Wenjie and Navigli, Roberto},
  pages = {3063--3074},
  publisher = {Association for Computational Linguistics},
  series = {Findings of {ACL}},
  volume = {{ACL/IJCNLP} 2021},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/acl/ChenCLCMWY21.bib},
  doi = {10.18653/V1/2021.FINDINGS-ACL.270},
  timestamp = {Thu, 23 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/2021.findings-acl.270}
}

Enriching Ontology with Temporal Commonsense for Low-Resource Audio Tagging

Zhiling Zhang , Zelin Zhou , Haifeng Tang , Guangwei Li , Mengyue Wu , and Kenny Q. Zhu

In CIKM ’21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1 - 5, 2021 , Oct 2021

Bib

@inproceedings{Zhang2021g,
  author = {Zhang, Zhiling and Zhou, Zelin and Tang, Haifeng and Li, Guangwei and Wu, Mengyue and Zhu, Kenny Q.},
  booktitle = {{CIKM} '21: The 30th {ACM} International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1 - 5, 2021},
  title = {Enriching Ontology with Temporal Commonsense for Low-Resource Audio Tagging},
  year = {2021},
  editor = {Demartini, Gianluca and Zuccon, Guido and Culpepper, J. Shane and Huang, Zi and Tong, Hanghang},
  pages = {3652--3656},
  publisher = {{ACM}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/cikm/ZhangZTLWZ21.bib},
  doi = {10.1145/3459637.3482097},
  timestamp = {Tue, 16 Aug 2022 23:04:38 +0200},
  url = {https://doi.org/10.1145/3459637.3482097}
}

Text-to-Audio Grounding: Building Correspondence Between Captions and Sound Events

Xuenan Xu , Heinrich Dinkel , Mengyue Wu, and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021 , Oct 2021

Bib

@inproceedings{Xu2021,
  author = {Xu, Xuenan and Dinkel, Heinrich and Wu, Mengyue and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  title = {Text-to-Audio Grounding: Building Correspondence Between Captions and Sound Events},
  year = {2021},
  pages = {606--610},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/XuDW021.bib},
  doi = {10.1109/ICASSP39728.2021.9414834},
  timestamp = {Thu, 08 Jul 2021 17:12:48 +0200},
  url = {https://doi.org/10.1109/ICASSP39728.2021.9414834}
}

Investigating Local and Global Information for Automated Audio Captioning with Transfer Learning

Xuenan Xu , Heinrich Dinkel , Mengyue Wu, Zeyu Xie , and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021 , Oct 2021

Bib

@inproceedings{Xu2021a,
  author = {Xu, Xuenan and Dinkel, Heinrich and Wu, Mengyue and Xie, Zeyu and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  title = {Investigating Local and Global Information for Automated Audio Captioning with Transfer Learning},
  year = {2021},
  pages = {905--909},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/XuDWX021.bib},
  doi = {10.1109/ICASSP39728.2021.9413982},
  timestamp = {Thu, 08 Jul 2021 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP39728.2021.9413982}
}

A Lightweight Framework for Online Voice Activity Detection in the Wild

Xuenan Xu , Heinrich Dinkel , Mengyue Wu, and Kai Yu

In Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021 , Oct 2021

Bib

@inproceedings{Xu2021b,
  author = {Xu, Xuenan and Dinkel, Heinrich and Wu, Mengyue and Yu, Kai},
  booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021},
  title = {A Lightweight Framework for Online Voice Activity Detection in the Wild},
  year = {2021},
  editor = {Hermansky, Hynek and Cernock{\'{y}}, Honza and Burget, Luk{\'{a}}s and Lamel, Lori and Scharenborg, Odette and Motl{\'{\i}}cek, Petr},
  pages = {371--375},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/XuDW021.bib},
  doi = {10.21437/INTERSPEECH.2021-1977},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2021-1977}
}

Audio Caption in a Car Setting with a Sentence-Level Loss

Xuenan Xu , Heinrich Dinkel , Mengyue Wu, and Kai Yu

In 12th International Symposium on Chinese Spoken Language Processing, ISCSLP 2021, Hong Kong, January 24-27, 2021 , Oct 2021

Bib

@inproceedings{Xu2021c,
  author = {Xu, Xuenan and Dinkel, Heinrich and Wu, Mengyue and Yu, Kai},
  booktitle = {12th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2021, Hong Kong, January 24-27, 2021},
  title = {Audio Caption in a Car Setting with a Sentence-Level Loss},
  year = {2021},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/XuDW021.bib},
  doi = {10.1109/ISCSLP49672.2021.9362117},
  timestamp = {Mon, 22 Mar 2021 16:16:13 +0100},
  url = {https://doi.org/10.1109/ISCSLP49672.2021.9362117}
}

DEPA: Self-Supervised Audio Embedding for Depression Detection

Pingyue Zhang , Mengyue Wu, Heinrich Dinkel , and Kai Yu

In MM ’21: ACM Multimedia Conference, Virtual Event, China, October 20 - 24, 2021 , Oct 2021

Bib

@inproceedings{Zhang2021h,
  author = {Zhang, Pingyue and Wu, Mengyue and Dinkel, Heinrich and Yu, Kai},
  booktitle = {{MM} '21: {ACM} Multimedia Conference, Virtual Event, China, October 20 - 24, 2021},
  title = {{DEPA:} Self-Supervised Audio Embedding for Depression Detection},
  year = {2021},
  editor = {Shen, Heng Tao and Zhuang, Yueting and Smith, John R. and Yang, Yang and C{\'{e}}sar, Pablo and Metze, Florian and Prabhakaran, Balakrishnan},
  pages = {135--143},
  publisher = {{ACM}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/mm/ZhangWD021.bib},
  doi = {10.1145/3474085.3479236},
  timestamp = {Fri, 02 Dec 2022 08:27:05 +0100},
  url = {https://doi.org/10.1145/3474085.3479236}
}

LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching

Boer Lyu , Lu Chen , Su Zhu , and Kai Yu

Bib

@inproceedings{Lyu2021,
  author = {Lyu, Boer and Chen, Lu and Zhu, Su and Yu, Kai},
  booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI} 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9, 2021},
  title = {{LET:} Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching},
  year = {2021},
  pages = {13498--13506},
  publisher = {{AAAI} Press},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/aaai/LyuCZ021.bib},
  doi = {10.1609/AAAI.V35I15.17592},
  timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
  url = {https://doi.org/10.1609/aaai.v35i15.17592}
}

LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations

Ruisheng Cao , Lu Chen , Zhi Chen , Yanbin Zhao , Su Zhu , and Kai Yu

In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021 , Oct 2021

Bib

@inproceedings{Cao2021,
  author = {Cao, Ruisheng and Chen, Lu and Chen, Zhi and Zhao, Yanbin and Zhu, Su and Yu, Kai},
  booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, {ACL/IJCNLP} 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021},
  title = {{LGESQL:} Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations},
  year = {2021},
  editor = {Zong, Chengqing and Xia, Fei and Li, Wenjie and Navigli, Roberto},
  pages = {2541--2555},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/acl/CaoC0ZZ020.bib},
  doi = {10.18653/V1/2021.ACL-LONG.198},
  timestamp = {Thu, 23 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/2021.acl-long.198}
}

WebSRC: A Dataset for Web-Based Structural Reading Comprehension

Xingyu Chen , Zihan Zhao , Lu Chen, Jiabao Ji , Danyang Zhang , Ao Luo , Yuxuan Xiong , and Kai Yu

In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021 , Oct 2021

Bib

@inproceedings{Chen2021f,
  author = {Chen, Xingyu and Zhao, Zihan and Chen, Lu and Ji, Jiabao and Zhang, Danyang and Luo, Ao and Xiong, Yuxuan and Yu, Kai},
  booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, {EMNLP} 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021},
  title = {WebSRC: {A} Dataset for Web-Based Structural Reading Comprehension},
  year = {2021},
  editor = {Moens, Marie{-}Francine and Huang, Xuanjing and Specia, Lucia and Yih, Scott Wen{-}tau},
  pages = {4173--4185},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/emnlp/ChenZCJZLX021.bib},
  doi = {10.18653/V1/2021.EMNLP-MAIN.343},
  timestamp = {Fri, 16 Feb 2024 08:27:36 +0100},
  url = {https://doi.org/10.18653/v1/2021.emnlp-main.343}
}

Glyph Enhanced Chinese Character Pre-Training for Lexical Sememe Prediction

Boer Lyu , Lu Chen, and Kai Yu

In Findings of the Association for Computational Linguistics: EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 16-20 November, 2021 , Oct 2021

Bib

@inproceedings{Lyu2021a,
  author = {Lyu, Boer and Chen, Lu and Yu, Kai},
  booktitle = {Findings of the Association for Computational Linguistics: {EMNLP} 2021, Virtual Event / Punta Cana, Dominican Republic, 16-20 November, 2021},
  title = {Glyph Enhanced Chinese Character Pre-Training for Lexical Sememe Prediction},
  year = {2021},
  editor = {Moens, Marie{-}Francine and Huang, Xuanjing and Specia, Lucia and Yih, Scott Wen{-}tau},
  pages = {4549--4555},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/emnlp/LyuC021.bib},
  doi = {10.18653/V1/2021.FINDINGS-EMNLP.386},
  timestamp = {Fri, 16 Feb 2024 08:27:36 +0100},
  url = {https://doi.org/10.18653/v1/2021.findings-emnlp.386}
}

Class-Based Neural Network Language Model for Second-Pass Rescoring in ASR

Lingfeng Dai , Qi Liu , and Kai Yu

In Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021 , Oct 2021

Bib

@inproceedings{Dai2021,
  author = {Dai, Lingfeng and Liu, Qi and Yu, Kai},
  booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021},
  title = {Class-Based Neural Network Language Model for Second-Pass Rescoring in {ASR}},
  year = {2021},
  editor = {Hermansky, Hynek and Cernock{\'{y}}, Honza and Burget, Luk{\'{a}}s and Lamel, Lori and Scharenborg, Odette and Motl{\'{\i}}cek, Petr},
  pages = {2022--2026},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/DaiLY21.bib},
  doi = {10.21437/INTERSPEECH.2021-1080},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2021-1080}
}

Rich Prosody Diversity Modelling with Phone-Level Mixture Density Network

Chenpeng Du , and Kai Yu

In Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021 , Oct 2021

Bib

@inproceedings{Du2021b,
  author = {Du, Chenpeng and Yu, Kai},
  booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021},
  title = {Rich Prosody Diversity Modelling with Phone-Level Mixture Density Network},
  year = {2021},
  editor = {Hermansky, Hynek and Cernock{\'{y}}, Honza and Burget, Luk{\'{a}}s and Lamel, Lori and Scharenborg, Odette and Motl{\'{\i}}cek, Petr},
  pages = {3136--3140},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/Du021.bib},
  doi = {10.21437/INTERSPEECH.2021-802},
  timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2021-802}
}

ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser

Zhi Chen , Lu Chen, Yanbin Zhao , Ruisheng Cao , Zihan Xu , Su Zhu , and Kai Yu

In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021, Online, June 6-11, 2021 , Oct 2021

Bib

@inproceedings{Chen2021g,
  author = {Chen, Zhi and Chen, Lu and Zhao, Yanbin and Cao, Ruisheng and Xu, Zihan and Zhu, Su and Yu, Kai},
  booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, {NAACL-HLT} 2021, Online, June 6-11, 2021},
  title = {ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser},
  year = {2021},
  editor = {Toutanova, Kristina and Rumshisky, Anna and Zettlemoyer, Luke and Hakkani{-}T{\"{u}}r, Dilek and Beltagy, Iz and Bethard, Steven and Cotterell, Ryan and Chakraborty, Tanmoy and Zhou, Yichao},
  pages = {5567--5577},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/naacl/ChenCZCXZY21.bib},
  doi = {10.18653/V1/2021.NAACL-MAIN.441},
  timestamp = {Thu, 23 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/2021.naacl-main.441}
}

Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRF

Su Zhu , Lu Chen, Ruisheng Cao , Zhi Chen , Qingliang Miao , and Kai Yu

In Natural Language Processing and Chinese Computing - 10th CCF International Conference, NLPCC 2021, Qingdao, China, October 13-17, 2021, Proceedings, Part I , Oct 2021

Bib

@inproceedings{Zhu2021,
  author = {Zhu, Su and Chen, Lu and Cao, Ruisheng and Chen, Zhi and Miao, Qingliang and Yu, Kai},
  booktitle = {Natural Language Processing and Chinese Computing - 10th {CCF} International Conference, {NLPCC} 2021, Qingdao, China, October 13-17, 2021, Proceedings, Part {I}},
  title = {Few-Shot {NLU} with Vector Projection Distance and Abstract Triangular {CRF}},
  year = {2021},
  editor = {Wang, Lu and Feng, Yansong and Hong, Yu and He, Ruifang},
  pages = {505--516},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  volume = {13028},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/nlpcc/ZhuCCCMY21.bib},
  doi = {10.1007/978-3-030-88480-2\_40},
  timestamp = {Wed, 28 Dec 2022 17:53:03 +0100},
  url = {https://doi.org/10.1007/978-3-030-88480-2\_40}
}

Relation-Aware Multi-hop Reasoning forVisual Dialog

Yao Zhao , Lu Chen, and Kai Yu

In Natural Language Processing and Chinese Computing - 10th CCF International Conference, NLPCC 2021, Qingdao, China, October 13-17, 2021, Proceedings, Part I , Oct 2021

Bib

@inproceedings{Zhao2021,
  author = {Zhao, Yao and Chen, Lu and Yu, Kai},
  booktitle = {Natural Language Processing and Chinese Computing - 10th {CCF} International Conference, {NLPCC} 2021, Qingdao, China, October 13-17, 2021, Proceedings, Part {I}},
  title = {Relation-Aware Multi-hop Reasoning forVisual Dialog},
  year = {2021},
  editor = {Wang, Lu and Feng, Yansong and Hong, Yu and He, Ruifang},
  pages = {810--821},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  volume = {13028},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/nlpcc/ZhaoCY21.bib},
  doi = {10.1007/978-3-030-88480-2\_65},
  timestamp = {Wed, 13 Apr 2022 01:00:00 +0200},
  url = {https://doi.org/10.1007/978-3-030-88480-2\_65}
}

Mixture Density Network for Phone-Level Prosody Modelling in Speech Synthesis

Chenpeng Du , and Kai Yu

CoRR, Oct 2021

Bib

@article{Du2021c,
  author = {Du, Chenpeng and Yu, Kai},
  journal = {CoRR},
  title = {Mixture Density Network for Phone-Level Prosody Modelling in Speech Synthesis},
  year = {2021},
  volume = {abs/2102.00851},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2102-00851.bib},
  eprint = {2102.00851},
  timestamp = {Fri, 09 Jul 2021 01:00:00 +0200},
  url = {https://arxiv.org/abs/2102.00851}
}

Diverse and Controllable Speech Synthesis with GMM-Based Phone-Level Prosody Modelling

Chenpeng Du , and Kai Yu

CoRR, Oct 2021

Bib

@article{Du2021d,
  author = {Du, Chenpeng and Yu, Kai},
  journal = {CoRR},
  title = {Diverse and Controllable Speech Synthesis with GMM-Based Phone-Level Prosody Modelling},
  year = {2021},
  volume = {abs/2105.13086},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2105-13086.bib},
  eprint = {2105.13086},
  timestamp = {Fri, 09 Jul 2021 01:00:00 +0200},
  url = {https://arxiv.org/abs/2105.13086}
}

2020

Improving End-to-End Single-Channel Multi-Talker Speech Recognition

Wangyou Zhang , Xuankai Chang , Yanmin Qian , and Shinji Watanabe

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2020

Bib

@article{Zhang2020,
  author = {Zhang, Wangyou and Chang, Xuankai and Qian, Yanmin and Watanabe, Shinji},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Improving End-to-End Single-Channel Multi-Talker Speech Recognition},
  year = {2020},
  pages = {1385--1394},
  volume = {28},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/ZhangCQW20.bib},
  doi = {10.1109/TASLP.2020.2988423},
  timestamp = {Fri, 26 Jun 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/TASLP.2020.2988423}
}

Data Augmentation Using Deep Generative Models for Embedding Based Speaker Recognition

Shuai Wang , Yexin Yang , Zhanghao Wu , Yanmin Qian , and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2020

Bib

@article{Wang2020,
  author = {Wang, Shuai and Yang, Yexin and Wu, Zhanghao and Qian, Yanmin and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Data Augmentation Using Deep Generative Models for Embedding Based Speaker Recognition},
  year = {2020},
  pages = {2598--2609},
  volume = {28},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/WangYWQY20.bib},
  doi = {10.1109/TASLP.2020.3016498},
  timestamp = {Tue, 06 Oct 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/TASLP.2020.3016498}
}

End-To-End Multi-Speaker Speech Recognition With Transformer

Xuankai Chang , Wangyou Zhang , Yanmin Qian , Jonathan Le Roux , and Shinji Watanabe

In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spain, May 4-8, 2020 , Oct 2020

Bib

@inproceedings{Chang2020,
  author = {Chang, Xuankai and Zhang, Wangyou and Qian, Yanmin and Roux, Jonathan Le and Watanabe, Shinji},
  booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
  title = {End-To-End Multi-Speaker Speech Recognition With Transformer},
  year = {2020},
  pages = {6134--6138},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ChangZQRW20.bib},
  doi = {10.1109/ICASSP40776.2020.9054029},
  timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP40776.2020.9054029}
}

Text Adaptation for Speaker Verification with Speaker-Text Factorized Embeddings

Yexin Yang , Shuai Wang , Xun Gong , Yanmin Qian , and Kai Yu

In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spain, May 4-8, 2020 , Oct 2020

Bib

@inproceedings{Yang2020,
  author = {Yang, Yexin and Wang, Shuai and Gong, Xun and Qian, Yanmin and Yu, Kai},
  booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
  title = {Text Adaptation for Speaker Verification with Speaker-Text Factorized Embeddings},
  year = {2020},
  pages = {6454--6458},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/Yang0GQ020.bib},
  doi = {10.1109/ICASSP40776.2020.9054333},
  timestamp = {Fri, 23 Sep 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP40776.2020.9054333}
}

Channel Invariant Speaker Embedding Learning with Joint Multi-Task and Adversarial Training

Zhengyang Chen , Shuai Wang , Yanmin Qian , and Kai Yu

In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spain, May 4-8, 2020 , Oct 2020

Bib

@inproceedings{Chen2020,
  author = {Chen, Zhengyang and Wang, Shuai and Qian, Yanmin and Yu, Kai},
  booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
  title = {Channel Invariant Speaker Embedding Learning with Joint Multi-Task and Adversarial Training},
  year = {2020},
  pages = {6574--6578},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/Chen0Q020.bib},
  doi = {10.1109/ICASSP40776.2020.9053905},
  timestamp = {Thu, 23 Jul 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP40776.2020.9053905}
}

Deep Audio-Visual Speech Separation with Attention Mechanism

Chenda Li , and Yanmin Qian

In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spain, May 4-8, 2020 , Oct 2020

Bib

@inproceedings{Li2020,
  author = {Li, Chenda and Qian, Yanmin},
  booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
  title = {Deep Audio-Visual Speech Separation with Attention Mechanism},
  year = {2020},
  pages = {7314--7318},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/LiQ20.bib},
  doi = {10.1109/ICASSP40776.2020.9054180},
  timestamp = {Thu, 23 Jul 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP40776.2020.9054180}
}

Learning Contextual Language Embeddings for Monaural Multi-Talker Speech Recognition

Wangyou Zhang , and Yanmin Qian

In Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020 , Oct 2020

Bib

@inproceedings{Zhang2020a,
  author = {Zhang, Wangyou and Qian, Yanmin},
  booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020},
  title = {Learning Contextual Language Embeddings for Monaural Multi-Talker Speech Recognition},
  year = {2020},
  editor = {Meng, Helen and Xu, Bo and Zheng, Thomas Fang},
  pages = {304--308},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ZhangQ20.bib},
  doi = {10.21437/INTERSPEECH.2020-2015},
  timestamp = {Fri, 29 Jan 2021 17:40:16 +0100},
  url = {https://doi.org/10.21437/Interspeech.2020-2015}
}

End-to-End Far-Field Speech Recognition with Unified Dereverberation and Beamforming

Wangyou Zhang , Aswin Shanmugam Subramanian , Xuankai Chang , Shinji Watanabe , and Yanmin Qian

In Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020 , Oct 2020

Bib

@inproceedings{Zhang2020b,
  author = {Zhang, Wangyou and Subramanian, Aswin Shanmugam and Chang, Xuankai and Watanabe, Shinji and Qian, Yanmin},
  booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020},
  title = {End-to-End Far-Field Speech Recognition with Unified Dereverberation and Beamforming},
  year = {2020},
  editor = {Meng, Helen and Xu, Bo and Zheng, Thomas Fang},
  pages = {324--328},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ZhangSC0Q20.bib},
  doi = {10.21437/INTERSPEECH.2020-2432},
  timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2020-2432}
}

Dual-Adversarial Domain Adaptation for Generalized Replay Attack Detection

Hongji Wang , Heinrich Dinkel , Shuai Wang , Yanmin Qian , and Kai Yu

In Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020 , Oct 2020

Bib

@inproceedings{Wang2020a,
  author = {Wang, Hongji and Dinkel, Heinrich and Wang, Shuai and Qian, Yanmin and Yu, Kai},
  booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020},
  title = {Dual-Adversarial Domain Adaptation for Generalized Replay Attack Detection},
  year = {2020},
  editor = {Meng, Helen and Xu, Bo and Zheng, Thomas Fang},
  pages = {1086--1090},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/WangD0Q020.bib},
  doi = {10.21437/INTERSPEECH.2020-1255},
  timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2020-1255}
}

Listen, Watch and Understand at the Cocktail Party: Audio-Visual-Contextual Speech Separation

Chenda Li , and Yanmin Qian

In Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020 , Oct 2020

Bib

@inproceedings{Li2020a,
  author = {Li, Chenda and Qian, Yanmin},
  booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020},
  title = {Listen, Watch and Understand at the Cocktail Party: Audio-Visual-Contextual Speech Separation},
  year = {2020},
  editor = {Meng, Helen and Xu, Bo and Zheng, Thomas Fang},
  pages = {1426--1430},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/LiQ20.bib},
  doi = {10.21437/INTERSPEECH.2020-2028},
  timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2020-2028}
}

Multi-Modality Matters: A Performance Leap on VoxCeleb

Zhengyang Chen , Shuai Wang , and Yanmin Qian

In Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020 , Oct 2020

Bib

@inproceedings{Chen2020a,
  author = {Chen, Zhengyang and Wang, Shuai and Qian, Yanmin},
  booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020},
  title = {Multi-Modality Matters: {A} Performance Leap on VoxCeleb},
  year = {2020},
  editor = {Meng, Helen and Xu, Bo and Zheng, Thomas Fang},
  pages = {2252--2256},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ChenWQ20.bib},
  doi = {10.21437/INTERSPEECH.2020-2229},
  timestamp = {Fri, 10 Mar 2023 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2020-2229}
}

Adversarial Domain Adaptation for Speaker Verification Using Partially Shared Network

Zhengyang Chen , Shuai Wang , and Yanmin Qian

In Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020 , Oct 2020

Bib

@inproceedings{Chen2020b,
  author = {Chen, Zhengyang and Wang, Shuai and Qian, Yanmin},
  booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020},
  title = {Adversarial Domain Adaptation for Speaker Verification Using Partially Shared Network},
  year = {2020},
  editor = {Meng, Helen and Xu, Bo and Zheng, Thomas Fang},
  pages = {3017--3021},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ChenWQ20a.bib},
  doi = {10.21437/INTERSPEECH.2020-2226},
  timestamp = {Fri, 10 Mar 2023 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2020-2226}
}

Bi-Encoder Transformer Network for Mandarin-English Code-Switching Speech Recognition Using Mixture of Experts

Yizhou Lu , Mingkun Huang , Hao Li , Jiaqi Guo , and Yanmin Qian

In Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020 , Oct 2020

Bib

@inproceedings{Lu2020,
  author = {Lu, Yizhou and Huang, Mingkun and Li, Hao and Guo, Jiaqi and Qian, Yanmin},
  booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020},
  title = {Bi-Encoder Transformer Network for Mandarin-English Code-Switching Speech Recognition Using Mixture of Experts},
  year = {2020},
  editor = {Meng, Helen and Xu, Bo and Zheng, Thomas Fang},
  pages = {4766--4770},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/LuHLGQ20.bib},
  doi = {10.21437/INTERSPEECH.2020-2485},
  timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2020-2485}
}

End-to-End Speaker-Dependent Voice Activity Detection

Yefei Chen , Shuai Wang , Yanmin Qian , and Kai Yu

CoRR, Oct 2020

Bib

@article{Chen2020c,
  author = {Chen, Yefei and Wang, Shuai and Qian, Yanmin and Yu, Kai},
  journal = {CoRR},
  title = {End-to-End Speaker-Dependent Voice Activity Detection},
  year = {2020},
  volume = {abs/2009.09906},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2009-09906.bib},
  eprint = {2009.09906},
  timestamp = {Wed, 23 Sep 2020 01:00:00 +0200},
  url = {https://arxiv.org/abs/2009.09906}
}

A CRNN-GRU Based Reinforcement Learning Approach to Audio Captioning

Xuenan Xu , Heinrich Dinkel , Mengyue Wu, and Kai Yu

In Proceedings of 5th the Workshop on Detection and Classification of Acoustic Scenes and Events 2020 (DCASE 2020), Tokyo, Japan (full virtual), November 2-4, 2020 , Oct 2020

Bib

@inproceedings{Xu2020,
  author = {Xu, Xuenan and Dinkel, Heinrich and Wu, Mengyue and Yu, Kai},
  booktitle = {Proceedings of 5th the Workshop on Detection and Classification of Acoustic Scenes and Events 2020 {(DCASE} 2020), Tokyo, Japan (full virtual), November 2-4, 2020},
  title = {A {CRNN-GRU} Based Reinforcement Learning Approach to Audio Captioning},
  year = {2020},
  editor = {Ono, Nobutaka and Harada, Noboru and Kawaguchi, Yohei and Mesaros, Annamaria and Imoto, Keisuke and Koizumi, Yuma and Komatsu, Tatsuya},
  pages = {225--229},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/dcase/XuDWY20.bib},
  timestamp = {Tue, 21 Dec 2021 00:00:00 +0100},
  url = {http://dcase.community/documents/workshop2020/proceedings/DCASE2020Workshop\_Xu\_83.pdf}
}

Multiple Sound Sources Localization from Coarse to Fine

Rui Qian , Di Hu , Heinrich Dinkel , Mengyue Wu, Ning Xu , and Weiyao Lin

In Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XX , Oct 2020

Bib

@inproceedings{Qian2020,
  author = {Qian, Rui and Hu, Di and Dinkel, Heinrich and Wu, Mengyue and Xu, Ning and Lin, Weiyao},
  booktitle = {Computer Vision - {ECCV} 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part {XX}},
  title = {Multiple Sound Sources Localization from Coarse to Fine},
  year = {2020},
  editor = {Vedaldi, Andrea and Bischof, Horst and Brox, Thomas and Frahm, Jan{-}Michael},
  pages = {292--308},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  volume = {12365},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/eccv/QianHDWXL20.bib},
  doi = {10.1007/978-3-030-58565-5\_18},
  timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
  url = {https://doi.org/10.1007/978-3-030-58565-5\_18}
}

Voice Activity Detection in the Wild via Weakly Supervised Sound Event Detection

Yefei Chen , Heinrich Dinkel , Mengyue Wu, and Kai Yu

In Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020 , Oct 2020

Bib

@inproceedings{Chen2020d,
  author = {Chen, Yefei and Dinkel, Heinrich and Wu, Mengyue and Yu, Kai},
  booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020},
  title = {Voice Activity Detection in the Wild via Weakly Supervised Sound Event Detection},
  year = {2020},
  editor = {Meng, Helen and Xu, Bo and Zheng, Thomas Fang},
  pages = {3665--3669},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ChenDW020.bib},
  doi = {10.21437/INTERSPEECH.2020-995},
  timestamp = {Tue, 27 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2020-995}
}

GPVAD: Towards noise robust voice activity detection via weakly supervised sound event detection

Heinrich Dinkel , Yefei Chen , Mengyue Wu, and Kai Yu

CoRR, Oct 2020

Bib

@article{Dinkel2020a,
  author = {Dinkel, Heinrich and Chen, Yefei and Wu, Mengyue and Yu, Kai},
  journal = {CoRR},
  title = {{GPVAD:} Towards noise robust voice activity detection via weakly supervised sound event detection},
  year = {2020},
  volume = {abs/2003.12222},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2003-12222.bib},
  eprint = {2003.12222},
  timestamp = {Wed, 01 Apr 2020 01:00:00 +0200},
  url = {https://arxiv.org/abs/2003.12222}
}

Interpreting Hierarchical Linguistic Interactions in DNNs

Die Zhang , Huilin Zhou , Xiaoyi Bao , Da Huo , Ruizhao Chen , Xu Cheng , Hao Zhang , Mengyue Wu, and Quanshi Zhang

CoRR, Oct 2020

Bib

@article{Zhang2020d,
  author = {Zhang, Die and Zhou, Huilin and Bao, Xiaoyi and Huo, Da and Chen, Ruizhao and Cheng, Xu and Zhang, Hao and Wu, Mengyue and Zhang, Quanshi},
  journal = {CoRR},
  title = {Interpreting Hierarchical Linguistic Interactions in DNNs},
  year = {2020},
  volume = {abs/2007.04298},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2007-04298.bib},
  eprint = {2007.04298},
  timestamp = {Fri, 07 Jan 2022 00:00:00 +0100},
  url = {https://arxiv.org/abs/2007.04298}
}

Towards a new generation of artificial intelligence in China

Fei Wu , Cewu Lu , Mingjie Zhu , Hao Chen , Jun Zhu , Kai Yu, Lei Li , Ming Li , Qianfeng Chen , Xi Li , Xudong Cao , Zhongyuan Wang , Zhengjun Zha , Yueting Zhuang , and Yunhe Pan

Nat. Mach. Intell., Oct 2020

Bib

@article{Wu2020,
  author = {Wu, Fei and Lu, Cewu and Zhu, Mingjie and Chen, Hao and Zhu, Jun and Yu, Kai and Li, Lei and Li, Ming and Chen, Qianfeng and Li, Xi and Cao, Xudong and Wang, Zhongyuan and Zha, Zhengjun and Zhuang, Yueting and Pan, Yunhe},
  journal = {Nat. Mach. Intell.},
  title = {Towards a new generation of artificial intelligence in China},
  year = {2020},
  number = {6},
  pages = {312--316},
  volume = {2},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/natmi/WuLZCZYLLCLCWZZ20.bib},
  doi = {10.1038/S42256-020-0183-4},
  timestamp = {Tue, 14 Mar 2023 00:00:00 +0100},
  url = {https://doi.org/10.1038/s42256-020-0183-4}
}

Prior Knowledge Driven Label Embedding for Slot Filling in Natural Language Understanding

Su Zhu , Zijian Zhao , Rao Ma , and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2020

Bib

@article{Zhu2020,
  author = {Zhu, Su and Zhao, Zijian and Ma, Rao and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Prior Knowledge Driven Label Embedding for Slot Filling in Natural Language Understanding},
  year = {2020},
  pages = {1440--1451},
  volume = {28},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/ZhuZMY20.bib},
  doi = {10.1109/TASLP.2020.2980152},
  timestamp = {Wed, 26 Aug 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/TASLP.2020.2980152}
}

Dual Learning for Semi-Supervised Natural Language Understanding

Su Zhu , Ruisheng Cao , and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2020

Bib

@article{Zhu2020a,
  author = {Zhu, Su and Cao, Ruisheng and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Dual Learning for Semi-Supervised Natural Language Understanding},
  year = {2020},
  pages = {1936--1947},
  volume = {28},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/ZhuCY20.bib},
  doi = {10.1109/TASLP.2020.3001684},
  timestamp = {Thu, 06 Aug 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/TASLP.2020.3001684}
}

Modular End-to-End Automatic Speech Recognition Framework for Acoustic-to-Word Model

Qi Liu , Zhehuai Chen , Hao Li , Mingkun Huang , Yizhou Lu , and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2020

Bib

@article{Liu2020a,
  author = {Liu, Qi and Chen, Zhehuai and Li, Hao and Huang, Mingkun and Lu, Yizhou and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Modular End-to-End Automatic Speech Recognition Framework for Acoustic-to-Word Model},
  year = {2020},
  pages = {2174--2183},
  volume = {28},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/LiuCLHLY20.bib},
  doi = {10.1109/TASLP.2020.3009477},
  timestamp = {Wed, 18 May 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/TASLP.2020.3009477}
}

Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management

Zhi Chen , Lu Chen, Xiaoyuan Liu , and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2020

Bib

@article{Chen2020e,
  author = {Chen, Zhi and Chen, Lu and Liu, Xiaoyuan and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management},
  year = {2020},
  pages = {2400--2411},
  volume = {28},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/ChenCLY20.bib},
  doi = {10.1109/TASLP.2020.3013392},
  timestamp = {Tue, 06 Oct 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/TASLP.2020.3013392}
}

Neural Network Language Model Compression With Product Quantization and Soft Binarization

Kai Yu, Rao Ma , Kaiyu Shi , and Qi Liu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2020

Bib

@article{Yu2020,
  author = {Yu, Kai and Ma, Rao and Shi, Kaiyu and Liu, Qi},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Neural Network Language Model Compression With Product Quantization and Soft Binarization},
  year = {2020},
  pages = {2438--2449},
  volume = {28},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/YuMSL20.bib},
  doi = {10.1109/TASLP.2020.3015659},
  timestamp = {Tue, 16 Aug 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/TASLP.2020.3015659}
}

Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks

Lu Chen, Boer Lv , Chi Wang , Su Zhu , Bowen Tan , and Kai Yu

In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020 , Oct 2020

Bib

@inproceedings{Chen2020f,
  author = {Chen, Lu and Lv, Boer and Wang, Chi and Zhu, Su and Tan, Bowen and Yu, Kai},
  booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA, February 7-12, 2020},
  title = {Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks},
  year = {2020},
  pages = {7521--7528},
  publisher = {{AAAI} Press},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/aaai/0002LWZT020.bib},
  doi = {10.1609/AAAI.V34I05.6250},
  timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
  url = {https://doi.org/10.1609/aaai.v34i05.6250}
}

Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising Autoencoders

Yanbin Zhao , Lu Chen , Zhi Chen , and Kai Yu

Bib

@inproceedings{Zhao2020,
  author = {Zhao, Yanbin and Chen, Lu and Chen, Zhi and Yu, Kai},
  booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA, February 7-12, 2020},
  title = {Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising Autoencoders},
  year = {2020},
  pages = {9668--9675},
  publisher = {{AAAI} Press},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/aaai/ZhaoCCY20.bib},
  doi = {10.1609/AAAI.V34I05.6515},
  timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
  url = {https://doi.org/10.1609/aaai.v34i05.6515}
}

Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention Networks

Yanbin Zhao , Lu Chen , Zhi Chen , Ruisheng Cao , Su Zhu , and Kai Yu

In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020 , Oct 2020

Bib

@inproceedings{Zhao2020a,
  author = {Zhao, Yanbin and Chen, Lu and Chen, Zhi and Cao, Ruisheng and Zhu, Su and Yu, Kai},
  booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, {ACL} 2020, Online, July 5-10, 2020},
  title = {Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention Networks},
  year = {2020},
  editor = {Jurafsky, Dan and Chai, Joyce and Schluter, Natalie and Tetreault, Joel R.},
  pages = {732--741},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/acl/ZhaoCCCZY20.bib},
  doi = {10.18653/V1/2020.ACL-MAIN.67},
  timestamp = {Thu, 23 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/2020.acl-main.67}
}

Neural Graph Matching Networks for Chinese Short Text Matching

Lu Chen, Yanbin Zhao , Boer Lyu , Lesheng Jin , Zhi Chen , Su Zhu , and Kai Yu

In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020 , Oct 2020

Bib

@inproceedings{Chen2020g,
  author = {Chen, Lu and Zhao, Yanbin and Lyu, Boer and Jin, Lesheng and Chen, Zhi and Zhu, Su and Yu, Kai},
  booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, {ACL} 2020, Online, July 5-10, 2020},
  title = {Neural Graph Matching Networks for Chinese Short Text Matching},
  year = {2020},
  editor = {Jurafsky, Dan and Chai, Joyce and Schluter, Natalie and Tetreault, Joel R.},
  pages = {6152--6158},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/acl/ChenZLJCZY20.bib},
  doi = {10.18653/V1/2020.ACL-MAIN.547},
  timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/2020.acl-main.547}
}

Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing

Ruisheng Cao , Su Zhu , Chenyu Yang , Chen Liu , Rao Ma , Yanbin Zhao , Lu Chen, and Kai Yu

In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020 , Oct 2020

Bib

@inproceedings{Cao2020,
  author = {Cao, Ruisheng and Zhu, Su and Yang, Chenyu and Liu, Chen and Ma, Rao and Zhao, Yanbin and Chen, Lu and Yu, Kai},
  booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, {ACL} 2020, Online, July 5-10, 2020},
  title = {Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing},
  year = {2020},
  editor = {Jurafsky, Dan and Chai, Joyce and Schluter, Natalie and Tetreault, Joel R.},
  pages = {6806--6817},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/acl/CaoZYLMZCY20.bib},
  doi = {10.18653/V1/2020.ACL-MAIN.608},
  timestamp = {Thu, 23 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/2020.acl-main.608}
}

Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking

Su Zhu , Jieyu Li , Lu Chen, and Kai Yu

In Findings of the Association for Computational Linguistics: EMNLP 2020, Online Event, 16-20 November 2020 , Oct 2020

Bib

@inproceedings{Zhu2020b,
  author = {Zhu, Su and Li, Jieyu and Chen, Lu and Yu, Kai},
  booktitle = {Findings of the Association for Computational Linguistics: {EMNLP} 2020, Online Event, 16-20 November 2020},
  title = {Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking},
  year = {2020},
  editor = {Cohn, Trevor and He, Yulan and Liu, Yang},
  pages = {766--781},
  publisher = {Association for Computational Linguistics},
  series = {Findings of {ACL}},
  volume = {{EMNLP} 2020},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/emnlp/ZhuL0020.bib},
  doi = {10.18653/V1/2020.FINDINGS-EMNLP.68},
  timestamp = {Wed, 23 Mar 2022 10:11:55 +0100},
  url = {https://doi.org/10.18653/v1/2020.findings-emnlp.68}
}

Duration Robust Weakly Supervised Sound Event Detection

Heinrich Dinkel , and Kai Yu

In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spain, May 4-8, 2020 , Oct 2020

Bib

@inproceedings{Dinkel2020b,
  author = {Dinkel, Heinrich and Yu, Kai},
  booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
  title = {Duration Robust Weakly Supervised Sound Event Detection},
  year = {2020},
  pages = {311--315},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/Dinkel020.bib},
  doi = {10.1109/ICASSP40776.2020.9053459},
  timestamp = {Thu, 23 Jul 2020 16:19:28 +0200},
  url = {https://doi.org/10.1109/ICASSP40776.2020.9053459}
}

Investigation of Specaugment for Deep Speaker Embedding Learning

Shuai Wang , Johan Rohdin , Oldrich Plchot , Lukás Burget , Kai Yu, and Jan Cernocký

In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spain, May 4-8, 2020 , Oct 2020

Bib

@inproceedings{Wang2020b,
  author = {Wang, Shuai and Rohdin, Johan and Plchot, Oldrich and Burget, Luk{\'{a}}s and Yu, Kai and Cernock{\'{y}}, Jan},
  booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
  title = {Investigation of Specaugment for Deep Speaker Embedding Learning},
  year = {2020},
  pages = {7139--7143},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/0016RPBYC20.bib},
  doi = {10.1109/ICASSP40776.2020.9053481},
  timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP40776.2020.9053481}
}

Speaker Augmentation for Low Resource Speech Recognition

Chenpeng Du , and Kai Yu

In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spain, May 4-8, 2020 , Oct 2020

Bib

@inproceedings{Du2020a,
  author = {Du, Chenpeng and Yu, Kai},
  booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
  title = {Speaker Augmentation for Low Resource Speech Recognition},
  year = {2020},
  pages = {7719--7723},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/DuY20.bib},
  doi = {10.1109/ICASSP40776.2020.9053139},
  timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP40776.2020.9053139}
}

Neural Lattice Search for Speech Recognition

Rao Ma , Hao Li , Qi Liu , Lu Chen, and Kai Yu

In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spain, May 4-8, 2020 , Oct 2020

Bib

@inproceedings{Ma2020,
  author = {Ma, Rao and Li, Hao and Liu, Qi and Chen, Lu and Yu, Kai},
  booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
  title = {Neural Lattice Search for Speech Recognition},
  year = {2020},
  pages = {7794--7798},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/MaLLCY20.bib},
  doi = {10.1109/ICASSP40776.2020.9054109},
  timestamp = {Wed, 18 May 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP40776.2020.9054109}
}

A Hierarchical Tracker for Multi-Domain Dialogue State Tracking

Jieyu Li , Su Zhu , and Kai Yu

In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spain, May 4-8, 2020 , Oct 2020

Bib

@inproceedings{Li2020b,
  author = {Li, Jieyu and Zhu, Su and Yu, Kai},
  booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
  title = {A Hierarchical Tracker for Multi-Domain Dialogue State Tracking},
  year = {2020},
  pages = {8014--8018},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/LiZY20.bib},
  doi = {10.1109/ICASSP40776.2020.9053248},
  timestamp = {Tue, 04 Aug 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP40776.2020.9053248}
}

Addressing the Polysemy Problem in Language Modeling with Attentional Multi-Sense Embeddings

Rao Ma , Lesheng Jin , Qi Liu , Lu Chen, and Kai Yu

In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spain, May 4-8, 2020 , Oct 2020

Bib

@inproceedings{Ma2020a,
  author = {Ma, Rao and Jin, Lesheng and Liu, Qi and Chen, Lu and Yu, Kai},
  booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
  title = {Addressing the Polysemy Problem in Language Modeling with Attentional Multi-Sense Embeddings},
  year = {2020},
  pages = {8129--8133},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/MaJLCY20.bib},
  doi = {10.1109/ICASSP40776.2020.9053503},
  timestamp = {Wed, 18 May 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP40776.2020.9053503}
}

CODA: Improving Resource Utilization by Slimming and Co-locating DNN and CPU Jobs

Han Zhao , Weihao Cui , Quan Chen , Jingwen Leng , Kai Yu, Deze Zeng , Chao Li , and Minyi Guo

In 40th IEEE International Conference on Distributed Computing Systems, ICDCS 2020, Singapore, November 29 - December 1, 2020 , Oct 2020

Bib

@inproceedings{Zhao2020b,
  author = {Zhao, Han and Cui, Weihao and Chen, Quan and Leng, Jingwen and Yu, Kai and Zeng, Deze and Li, Chao and Guo, Minyi},
  booktitle = {40th {IEEE} International Conference on Distributed Computing Systems, {ICDCS} 2020, Singapore, November 29 - December 1, 2020},
  title = {{CODA:} Improving Resource Utilization by Slimming and Co-locating {DNN} and {CPU} Jobs},
  year = {2020},
  pages = {853--863},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icdcs/0005CCLYZ0G20.bib},
  doi = {10.1109/ICDCS47774.2020.00069},
  timestamp = {Sat, 18 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICDCS47774.2020.00069}
}

Jointly Encoding Word Confusion Network and Dialogue Context with BERT for Spoken Language Understanding

Chen Liu , Su Zhu , Zijian Zhao , Ruisheng Cao , Lu Chen, and Kai Yu

In Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020 , Oct 2020

Bib

@inproceedings{Liu2020b,
  author = {Liu, Chen and Zhu, Su and Zhao, Zijian and Cao, Ruisheng and Chen, Lu and Yu, Kai},
  booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020},
  title = {Jointly Encoding Word Confusion Network and Dialogue Context with {BERT} for Spoken Language Understanding},
  year = {2020},
  editor = {Meng, Helen and Xu, Bo and Zheng, Thomas Fang},
  pages = {871--875},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/LiuZZC0020.bib},
  doi = {10.21437/INTERSPEECH.2020-1632},
  timestamp = {Thu, 23 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2020-1632}
}

Memory Attention Neural Network for Multi-domain Dialogue State Tracking

Zihan Xu , Zhi Chen , Lu Chen , Su Zhu , and Kai Yu

In Natural Language Processing and Chinese Computing - 9th CCF International Conference, NLPCC 2020, Zhengzhou, China, October 14-18, 2020, Proceedings, Part I , Oct 2020

Bib

@inproceedings{Xu2020a,
  author = {Xu, Zihan and Chen, Zhi and Chen, Lu and Zhu, Su and Yu, Kai},
  booktitle = {Natural Language Processing and Chinese Computing - 9th {CCF} International Conference, {NLPCC} 2020, Zhengzhou, China, October 14-18, 2020, Proceedings, Part {I}},
  title = {Memory Attention Neural Network for Multi-domain Dialogue State Tracking},
  year = {2020},
  editor = {Zhu, Xiaodan and Zhang, Min and Hong, Yu and He, Ruifang},
  pages = {41--52},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  volume = {12430},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/nlpcc/XuCCZY20.bib},
  doi = {10.1007/978-3-030-60450-9\_4},
  timestamp = {Wed, 20 Dec 2023 17:00:52 +0100},
  url = {https://doi.org/10.1007/978-3-030-60450-9\_4}
}

Robust Spoken Language Understanding with RL-Based Value Error Recovery

Chen Liu , Su Zhu , Lu Chen, and Kai Yu

In Natural Language Processing and Chinese Computing - 9th CCF International Conference, NLPCC 2020, Zhengzhou, China, October 14-18, 2020, Proceedings, Part I , Oct 2020

Bib

@inproceedings{Liu2020c,
  author = {Liu, Chen and Zhu, Su and Chen, Lu and Yu, Kai},
  booktitle = {Natural Language Processing and Chinese Computing - 9th {CCF} International Conference, {NLPCC} 2020, Zhengzhou, China, October 14-18, 2020, Proceedings, Part {I}},
  title = {Robust Spoken Language Understanding with RL-Based Value Error Recovery},
  year = {2020},
  editor = {Zhu, Xiaodan and Zhang, Min and Hong, Yu and He, Ruifang},
  pages = {78--90},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  volume = {12430},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/nlpcc/LiuZCY20.bib},
  doi = {10.1007/978-3-030-60450-9\_7},
  timestamp = {Wed, 05 May 2021 01:00:00 +0200},
  url = {https://doi.org/10.1007/978-3-030-60450-9\_7}
}

An Investigation on Different Underlying Quantization Schemes for Pre-trained Language Models

Zihan Zhao , Yuncong Liu , Lu Chen, Qi Liu , Rao Ma , and Kai Yu

In Natural Language Processing and Chinese Computing - 9th CCF International Conference, NLPCC 2020, Zhengzhou, China, October 14-18, 2020, Proceedings, Part I , Oct 2020

Bib

@inproceedings{Zhao2020c,
  author = {Zhao, Zihan and Liu, Yuncong and Chen, Lu and Liu, Qi and Ma, Rao and Yu, Kai},
  booktitle = {Natural Language Processing and Chinese Computing - 9th {CCF} International Conference, {NLPCC} 2020, Zhengzhou, China, October 14-18, 2020, Proceedings, Part {I}},
  title = {An Investigation on Different Underlying Quantization Schemes for Pre-trained Language Models},
  year = {2020},
  editor = {Zhu, Xiaodan and Zhang, Min and Hong, Yu and He, Ruifang},
  pages = {359--371},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  volume = {12430},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/nlpcc/ZhaoLCLMY20.bib},
  doi = {10.1007/978-3-030-60450-9\_29},
  timestamp = {Wed, 18 May 2022 01:00:00 +0200},
  url = {https://doi.org/10.1007/978-3-030-60450-9\_29}
}

An Investigation on Deep Learning with Beta Stabilizer

Qi Liu , Tian Tan , and Kai Yu

CoRR, Oct 2020

Bib

@article{Liu2020f,
  author = {Liu, Qi and Tan, Tian and Yu, Kai},
  journal = {CoRR},
  title = {An Investigation on Deep Learning with Beta Stabilizer},
  year = {2020},
  volume = {abs/2008.01173},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2008-01173.bib},
  eprint = {2008.01173},
  timestamp = {Wed, 18 May 2022 01:00:00 +0200},
  url = {https://arxiv.org/abs/2008.01173}
}

Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding

Su Zhu , Ruisheng Cao , Lu Chen, and Kai Yu

CoRR, Oct 2020

Bib

@article{Zhu2020f,
  author = {Zhu, Su and Cao, Ruisheng and Chen, Lu and Yu, Kai},
  journal = {CoRR},
  title = {Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding},
  year = {2020},
  volume = {abs/2009.09568},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2009-09568.bib},
  eprint = {2009.09568},
  timestamp = {Thu, 24 Sep 2020 01:00:00 +0200},
  url = {https://arxiv.org/abs/2009.09568}
}

Deep Reinforcement Learning for On-line Dialogue State Tracking

Zhi Chen , Lu Chen, Xiang Zhou , and Kai Yu

CoRR, Oct 2020

Bib

@article{Chen2020h,
  author = {Chen, Zhi and Chen, Lu and Zhou, Xiang and Yu, Kai},
  journal = {CoRR},
  title = {Deep Reinforcement Learning for On-line Dialogue State Tracking},
  year = {2020},
  volume = {abs/2009.10321},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2009-10321.bib},
  eprint = {2009.10321},
  timestamp = {Wed, 07 Oct 2020 01:00:00 +0200},
  url = {https://arxiv.org/abs/2009.10321}
}

Structured Hierarchical Dialogue Policy with Graph Neural Networks

Zhi Chen , Xiaoyuan Liu , Lu Chen, and Kai Yu

CoRR, Oct 2020

Bib

@article{Chen2020j,
  author = {Chen, Zhi and Liu, Xiaoyuan and Chen, Lu and Yu, Kai},
  journal = {CoRR},
  title = {Structured Hierarchical Dialogue Policy with Graph Neural Networks},
  year = {2020},
  volume = {abs/2009.10355},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2009-10355.bib},
  eprint = {2009.10355},
  timestamp = {Wed, 07 Oct 2020 01:00:00 +0200},
  url = {https://arxiv.org/abs/2009.10355}
}

Dual Learning for Dialogue State Tracking

Zhi Chen , Lu Chen, Yanbin Zhao , Su Zhu , and Kai Yu

CoRR, Oct 2020

Bib

@article{Chen2020k,
  author = {Chen, Zhi and Chen, Lu and Zhao, Yanbin and Zhu, Su and Yu, Kai},
  journal = {CoRR},
  title = {Dual Learning for Dialogue State Tracking},
  year = {2020},
  volume = {abs/2009.10430},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2009-10430.bib},
  eprint = {2009.10430},
  timestamp = {Wed, 07 Oct 2020 01:00:00 +0200},
  url = {https://arxiv.org/abs/2009.10430}
}

CREDIT: Coarse-to-Fine Sequence Generation for Dialogue State Tracking

Zhi Chen , Lu Chen, Zihan Xu , Yanbin Zhao , Su Zhu , and Kai Yu

CoRR, Oct 2020

Bib

@article{Chen2020l,
  author = {Chen, Zhi and Chen, Lu and Xu, Zihan and Zhao, Yanbin and Zhu, Su and Yu, Kai},
  journal = {CoRR},
  title = {{CREDIT:} Coarse-to-Fine Sequence Generation for Dialogue State Tracking},
  year = {2020},
  volume = {abs/2009.10435},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-2009-10435.bib},
  eprint = {2009.10435},
  timestamp = {Wed, 07 Oct 2020 01:00:00 +0200},
  url = {https://arxiv.org/abs/2009.10435}
}

2019

Erratum to: Past review, current progress, and challenges ahead on the cocktail party problem

Yanmin Qian , Chao Weng , Xuankai Chang , Shuai Wang , and Dong Yu

Frontiers Inf. Technol. Electron. Eng., Oct 2019

Bib

@article{Qian2019,
  author = {Qian, Yanmin and Weng, Chao and Chang, Xuankai and Wang, Shuai and Yu, Dong},
  journal = {Frontiers Inf. Technol. Electron. Eng.},
  title = {Erratum to: Past review, current progress, and challenges ahead on the cocktail party problem},
  year = {2019},
  number = {3},
  pages = {438},
  volume = {20},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/jzusc/QianWCWY19.bib},
  doi = {10.1631/FITEE.19E0001},
  timestamp = {Thu, 05 Mar 2020 00:00:00 +0100},
  url = {https://doi.org/10.1631/FITEE.19e0001}
}

Binary neural networks for speech recognition

Yanmin Qian , and Xu Xiang

Frontiers Inf. Technol. Electron. Eng., Oct 2019

Bib

@article{Qian2019a,
  author = {Qian, Yanmin and Xiang, Xu},
  journal = {Frontiers Inf. Technol. Electron. Eng.},
  title = {Binary neural networks for speech recognition},
  year = {2019},
  number = {5},
  pages = {701--715},
  volume = {20},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/jzusc/QianX19.bib},
  doi = {10.1631/FITEE.1800469},
  timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
  url = {https://doi.org/10.1631/fitee.1800469}
}

Data augmentation using generative adversarial networks for robust speech recognition

Yanmin Qian , Hu Hu , and Tian Tan

Speech Commun., Oct 2019

Bib

@article{Qian2019b,
  author = {Qian, Yanmin and Hu, Hu and Tan, Tian},
  journal = {Speech Commun.},
  title = {Data augmentation using generative adversarial networks for robust speech recognition},
  year = {2019},
  pages = {1--9},
  volume = {114},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/speech/QianHT19.bib},
  doi = {10.1016/J.SPECOM.2019.08.006},
  timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
  url = {https://doi.org/10.1016/j.specom.2019.08.006}
}

Discriminative Neural Embedding Learning for Short-Duration Text-Independent Speaker Verification

Shuai Wang , Zili Huang , Yanmin Qian , and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2019

Bib

@article{Wang2019,
  author = {Wang, Shuai and Huang, Zili and Qian, Yanmin and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Discriminative Neural Embedding Learning for Short-Duration Text-Independent Speaker Verification},
  year = {2019},
  number = {11},
  pages = {1686--1696},
  volume = {27},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/WangHQY19.bib},
  doi = {10.1109/TASLP.2019.2928128},
  timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2019.2928128}
}

Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition

Xu Xiang , Shuai Wang , Houjun Huang , Yanmin Qian , and Kai Yu

In 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019, Lanzhou, China, November 18-21, 2019 , Oct 2019

Bib

@inproceedings{Xiang2019,
  author = {Xiang, Xu and Wang, Shuai and Huang, Houjun and Qian, Yanmin and Yu, Kai},
  booktitle = {2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2019, Lanzhou, China, November 18-21, 2019},
  title = {Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition},
  year = {2019},
  pages = {1652--1656},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/apsipa/XiangWHQ019.bib},
  doi = {10.1109/APSIPAASC47483.2019.9023039},
  timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023039}
}

GANs for Children: A Generative Data Augmentation Strategy for Children Speech Recognition

Peiyao Sheng , Zhuolin Yang , and Yanmin Qian

In IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019, Singapore, December 14-18, 2019 , Oct 2019

Bib

@inproceedings{Sheng2019,
  author = {Sheng, Peiyao and Yang, Zhuolin and Qian, Yanmin},
  booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU} 2019, Singapore, December 14-18, 2019},
  title = {GANs for Children: {A} Generative Data Augmentation Strategy for Children Speech Recognition},
  year = {2019},
  pages = {129--135},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/asru/ShengYQ19.bib},
  doi = {10.1109/ASRU46091.2019.9003933},
  timestamp = {Mon, 24 Feb 2020 17:51:31 +0100},
  url = {https://doi.org/10.1109/ASRU46091.2019.9003933}
}

MIMO-Speech: End-to-End Multi-Channel Multi-Speaker Speech Recognition

Xuankai Chang , Wangyou Zhang , Yanmin Qian , Jonathan Le Roux , and Shinji Watanabe

In IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019, Singapore, December 14-18, 2019 , Oct 2019

Bib

@inproceedings{Chang2019,
  author = {Chang, Xuankai and Zhang, Wangyou and Qian, Yanmin and Roux, Jonathan Le and Watanabe, Shinji},
  booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU} 2019, Singapore, December 14-18, 2019},
  title = {MIMO-Speech: End-to-End Multi-Channel Multi-Speaker Speech Recognition},
  year = {2019},
  pages = {237--244},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/asru/ChangZQRW19.bib},
  doi = {10.1109/ASRU46091.2019.9003986},
  timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
  url = {https://doi.org/10.1109/ASRU46091.2019.9003986}
}

Exploring Model Units and Training Strategies for End-to-End Speech Recognition

Mingkun Huang , Yizhou Lu , Lan Wang , Yanmin Qian , and Kai Yu

In IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019, Singapore, December 14-18, 2019 , Oct 2019

Bib

@inproceedings{Huang2019,
  author = {Huang, Mingkun and Lu, Yizhou and Wang, Lan and Qian, Yanmin and Yu, Kai},
  booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU} 2019, Singapore, December 14-18, 2019},
  title = {Exploring Model Units and Training Strategies for End-to-End Speech Recognition},
  year = {2019},
  pages = {524--531},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/asru/HuangLWQY19.bib},
  doi = {10.1109/ASRU46091.2019.9003834},
  timestamp = {Mon, 24 Feb 2020 00:00:00 +0100},
  url = {https://doi.org/10.1109/ASRU46091.2019.9003834}
}

End-to-End Overlapped Speech Detection and Speaker Counting with Raw Waveform

Wangyou Zhang , Man Sun , Lan Wang , and Yanmin Qian

In IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019, Singapore, December 14-18, 2019 , Oct 2019

Bib

@inproceedings{Zhang2019,
  author = {Zhang, Wangyou and Sun, Man and Wang, Lan and Qian, Yanmin},
  booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU} 2019, Singapore, December 14-18, 2019},
  title = {End-to-End Overlapped Speech Detection and Speaker Counting with Raw Waveform},
  year = {2019},
  pages = {660--666},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/asru/ZhangSWQ19.bib},
  doi = {10.1109/ASRU46091.2019.9003962},
  timestamp = {Mon, 24 Feb 2020 00:00:00 +0100},
  url = {https://doi.org/10.1109/ASRU46091.2019.9003962}
}

Knowledge Distillation for Small Foot-print Deep Speaker Embedding

Shuai Wang , Yexin Yang , Tianzhe Wang , Yanmin Qian , and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2019, Brighton, United Kingdom, May 12-17, 2019 , Oct 2019

Bib

@inproceedings{Wang2019a,
  author = {Wang, Shuai and Yang, Yexin and Wang, Tianzhe and Qian, Yanmin and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
  title = {Knowledge Distillation for Small Foot-print Deep Speaker Embedding},
  year = {2019},
  pages = {6021--6025},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/WangYWQ019.bib},
  doi = {10.1109/ICASSP.2019.8683443},
  timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
  url = {https://doi.org/10.1109/ICASSP.2019.8683443}
}

End-to-end Monaural Multi-speaker ASR System without Pretraining

Xuankai Chang , Yanmin Qian , Kai Yu, and Shinji Watanabe

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2019, Brighton, United Kingdom, May 12-17, 2019 , Oct 2019

Bib

@inproceedings{Chang2019a,
  author = {Chang, Xuankai and Qian, Yanmin and Yu, Kai and Watanabe, Shinji},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
  title = {End-to-end Monaural Multi-speaker {ASR} System without Pretraining},
  year = {2019},
  pages = {6256--6260},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ChangQ0W19.bib},
  doi = {10.1109/ICASSP.2019.8682822},
  timestamp = {Fri, 26 Jun 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2019.8682822}
}

The SJTU Robust Anti-Spoofing System for the ASVspoof 2019 Challenge

Yexin Yang , Hongji Wang , Heinrich Dinkel , Zhengyang Chen , Shuai Wang , Yanmin Qian , and Kai Yu

In Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019 , Oct 2019

Bib

@inproceedings{Yang2019,
  author = {Yang, Yexin and Wang, Hongji and Dinkel, Heinrich and Chen, Zhengyang and Wang, Shuai and Qian, Yanmin and Yu, Kai},
  booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019},
  title = {The {SJTU} Robust Anti-Spoofing System for the ASVspoof 2019 Challenge},
  year = {2019},
  editor = {Kubin, Gernot and Kacic, Zdravko},
  pages = {1038--1042},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/YangWDCWQ019.bib},
  doi = {10.21437/INTERSPEECH.2019-2170},
  timestamp = {Fri, 29 Jan 2021 17:41:10 +0100},
  url = {https://doi.org/10.21437/Interspeech.2019-2170}
}

On the Usage of Phonetic Information for Text-Independent Speaker Embedding Extraction

Shuai Wang , Johan Rohdin , Lukás Burget , Oldrich Plchot , Yanmin Qian , Kai Yu, and Jan Cernocký

In Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019 , Oct 2019

Bib

@inproceedings{Wang2019b,
  author = {Wang, Shuai and Rohdin, Johan and Burget, Luk{\'{a}}s and Plchot, Oldrich and Qian, Yanmin and Yu, Kai and Cernock{\'{y}}, Jan},
  booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019},
  title = {On the Usage of Phonetic Information for Text-Independent Speaker Embedding Extraction},
  year = {2019},
  editor = {Kubin, Gernot and Kacic, Zdravko},
  pages = {1148--1152},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/WangRBPQ0C19.bib},
  doi = {10.21437/INTERSPEECH.2019-3036},
  timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2019-3036}
}

Data Augmentation Using Variational Autoencoder for Embedding Based Speaker Verification

Zhanghao Wu , Shuai Wang , Yanmin Qian , and Kai Yu

In Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019 , Oct 2019

Bib

@inproceedings{Wu2019,
  author = {Wu, Zhanghao and Wang, Shuai and Qian, Yanmin and Yu, Kai},
  booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019},
  title = {Data Augmentation Using Variational Autoencoder for Embedding Based Speaker Verification},
  year = {2019},
  editor = {Kubin, Gernot and Kacic, Zdravko},
  pages = {1163--1167},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/WuWQ019.bib},
  doi = {10.21437/INTERSPEECH.2019-2248},
  timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2019-2248}
}

Joint Decoding of CTC Based Systems for Speech Recognition

Jiaqi Guo , Yongbin You , Yanmin Qian , and Kai Yu

In Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019 , Oct 2019

Bib

@inproceedings{Guo2019,
  author = {Guo, Jiaqi and You, Yongbin and Qian, Yanmin and Yu, Kai},
  booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019},
  title = {Joint Decoding of {CTC} Based Systems for Speech Recognition},
  year = {2019},
  editor = {Kubin, Gernot and Kacic, Zdravko},
  pages = {2205--2209},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/GuoYQ019.bib},
  doi = {10.21437/INTERSPEECH.2019-2026},
  timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2019-2026}
}

Knowledge Distillation for End-to-End Monaural Multi-Talker ASR System

Wangyou Zhang , Xuankai Chang , and Yanmin Qian

In Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019 , Oct 2019

Bib

@inproceedings{Zhang2019a,
  author = {Zhang, Wangyou and Chang, Xuankai and Qian, Yanmin},
  booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019},
  title = {Knowledge Distillation for End-to-End Monaural Multi-Talker {ASR} System},
  year = {2019},
  editor = {Kubin, Gernot and Kacic, Zdravko},
  pages = {2633--2637},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ZhangCQ19.bib},
  doi = {10.21437/INTERSPEECH.2019-3192},
  timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2019-3192}
}

Robust DOA Estimation Based on Convolutional Neural Network and Time-Frequency Masking

Wangyou Zhang , Ying Zhou , and Yanmin Qian

In Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019 , Oct 2019

Bib

@inproceedings{Zhang2019b,
  author = {Zhang, Wangyou and Zhou, Ying and Qian, Yanmin},
  booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019},
  title = {Robust {DOA} Estimation Based on Convolutional Neural Network and Time-Frequency Masking},
  year = {2019},
  editor = {Kubin, Gernot and Kacic, Zdravko},
  pages = {2703--2707},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ZhangZQ19.bib},
  doi = {10.21437/INTERSPEECH.2019-3158},
  timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2019-3158}
}

Cross-Domain Replay Spoofing Attack Detection Using Domain Adversarial Training

Hongji Wang , Heinrich Dinkel , Shuai Wang , Yanmin Qian , and Kai Yu

In Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019 , Oct 2019

Bib

@inproceedings{Wang2019c,
  author = {Wang, Hongji and Dinkel, Heinrich and Wang, Shuai and Qian, Yanmin and Yu, Kai},
  booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019},
  title = {Cross-Domain Replay Spoofing Attack Detection Using Domain Adversarial Training},
  year = {2019},
  editor = {Kubin, Gernot and Kacic, Zdravko},
  pages = {2938--2942},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/WangD0Q019.bib},
  doi = {10.21437/INTERSPEECH.2019-2120},
  timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2019-2120}
}

Prosody Usage Optimization for Children Speech Recognition with Zero Resource Children Speech

Chenda Li , and Yanmin Qian

In Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019 , Oct 2019

Bib

@inproceedings{Li2019,
  author = {Li, Chenda and Qian, Yanmin},
  booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019},
  title = {Prosody Usage Optimization for Children Speech Recognition with Zero Resource Children Speech},
  year = {2019},
  editor = {Kubin, Gernot and Kacic, Zdravko},
  pages = {3446--3450},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/LiQ19.bib},
  doi = {10.21437/INTERSPEECH.2019-2659},
  timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2019-2659}
}

Audio Caption: Listen and Tell

Mengyue Wu, Heinrich Dinkel , and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2019, Brighton, United Kingdom, May 12-17, 2019 , Oct 2019

Bib

@inproceedings{Wu2019a,
  author = {Wu, Mengyue and Dinkel, Heinrich and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
  title = {Audio Caption: Listen and Tell},
  year = {2019},
  pages = {830--834},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/WuD019.bib},
  doi = {10.1109/ICASSP.2019.8682377},
  timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
  url = {https://doi.org/10.1109/ICASSP.2019.8682377}
}

Text-based Depression Detection: What Triggers An Alert

Heinrich Dinkel , Mengyue Wu, and Kai Yu

CoRR, Oct 2019

Bib

@article{Dinkel2019,
  author = {Dinkel, Heinrich and Wu, Mengyue and Yu, Kai},
  journal = {CoRR},
  title = {Text-based Depression Detection: What Triggers An Alert},
  year = {2019},
  volume = {abs/1904.05154},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-1904-05154.bib},
  eprint = {1904.05154},
  timestamp = {Thu, 25 Apr 2019 01:00:00 +0200},
  url = {http://arxiv.org/abs/1904.05154}
}

What does a Car-ssette tape tell?

Xuenan Xu , Heinrich Dinkel , Mengyue Wu, and Kai Yu

CoRR, Oct 2019

Bib

@article{Xu2019,
  author = {Xu, Xuenan and Dinkel, Heinrich and Wu, Mengyue and Yu, Kai},
  journal = {CoRR},
  title = {What does a Car-ssette tape tell?},
  year = {2019},
  volume = {abs/1905.13448},
  archiveprefix = {arXiv},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/corr/abs-1905-13448.bib},
  eprint = {1905.13448},
  timestamp = {Mon, 03 Jun 2019 01:00:00 +0200},
  url = {http://arxiv.org/abs/1905.13448}
}

AgentGraph: Toward Universal Dialogue Management With Structured Deep Reinforcement Learning

Lu Chen , Zhi Chen , Bowen Tan , Sishan Long , Milica Gasic , and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2019

Bib

@article{Chen2019,
  author = {Chen, Lu and Chen, Zhi and Tan, Bowen and Long, Sishan and Gasic, Milica and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {AgentGraph: Toward Universal Dialogue Management With Structured Deep Reinforcement Learning},
  year = {2019},
  number = {9},
  pages = {1378--1391},
  volume = {27},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/ChenCTLGY19.bib},
  doi = {10.1109/TASLP.2019.2919872},
  timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2019.2919872}
}

Semantic Parsing with Dual Learning

Ruisheng Cao , Su Zhu , Chen Liu , Jieyu Li , and Kai Yu

In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers , Oct 2019

Bib

@inproceedings{Cao2019,
  author = {Cao, Ruisheng and Zhu, Su and Liu, Chen and Li, Jieyu and Yu, Kai},
  booktitle = {Proceedings of the 57th Conference of the Association for Computational Linguistics, {ACL} 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers},
  title = {Semantic Parsing with Dual Learning},
  year = {2019},
  editor = {Korhonen, Anna and Traum, David R. and M{\`{a}}rquez, Llu{\'{\i}}s},
  pages = {51--64},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/acl/CaoZLLY19.bib},
  doi = {10.18653/V1/P19-1007},
  timestamp = {Thu, 23 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/p19-1007}
}

Highly Efficient Neural Network Language Model Compression Using Soft Binarization Training

Rao Ma , Qi Liu , and Kai Yu

In IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019, Singapore, December 14-18, 2019 , Oct 2019

Bib

@inproceedings{Ma2019,
  author = {Ma, Rao and Liu, Qi and Yu, Kai},
  booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU} 2019, Singapore, December 14-18, 2019},
  title = {Highly Efficient Neural Network Language Model Compression Using Soft Binarization Training},
  year = {2019},
  pages = {62--69},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/asru/MaLY19.bib},
  doi = {10.1109/ASRU46091.2019.9003744},
  timestamp = {Wed, 18 May 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ASRU46091.2019.9003744}
}

Data Augmentation with Atomic Templates for Spoken Language Understanding

Zijian Zhao , Su Zhu , and Kai Yu

In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019 , Oct 2019

Bib

@inproceedings{Zhao2019,
  author = {Zhao, Zijian and Zhu, Su and Yu, Kai},
  booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, {EMNLP-IJCNLP} 2019, Hong Kong, China, November 3-7, 2019},
  title = {Data Augmentation with Atomic Templates for Spoken Language Understanding},
  year = {2019},
  editor = {Inui, Kentaro and Jiang, Jing and Ng, Vincent and Wan, Xiaojun},
  pages = {3635--3641},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/emnlp/ZhaoZY19.bib},
  doi = {10.18653/V1/D19-1375},
  timestamp = {Thu, 07 Apr 2022 09:14:07 +0200},
  url = {https://doi.org/10.18653/v1/D19-1375}
}

A Hierarchical Decoding Model for Spoken Language Understanding from Unaligned Data

Zijian Zhao , Su Zhu , and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2019, Brighton, United Kingdom, May 12-17, 2019 , Oct 2019

Bib

@inproceedings{Zhao2019a,
  author = {Zhao, Zijian and Zhu, Su and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
  title = {A Hierarchical Decoding Model for Spoken Language Understanding from Unaligned Data},
  year = {2019},
  pages = {7305--7309},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ZhaoZY19.bib},
  doi = {10.1109/ICASSP.2019.8682463},
  timestamp = {Thu, 29 Aug 2019 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2019.8682463}
}

CATSLU: The 1st Chinese Audio-Textual Spoken Language Understanding Challenge

Su Zhu , Zijian Zhao , Tiejun Zhao , Chengqing Zong , and Kai Yu

In International Conference on Multimodal Interaction, ICMI 2019, Suzhou, China, October 14-18, 2019 , Oct 2019

Bib

@inproceedings{Zhu2019,
  author = {Zhu, Su and Zhao, Zijian and Zhao, Tiejun and Zong, Chengqing and Yu, Kai},
  booktitle = {International Conference on Multimodal Interaction, {ICMI} 2019, Suzhou, China, October 14-18, 2019},
  title = {{CATSLU:} The 1st Chinese Audio-Textual Spoken Language Understanding Challenge},
  year = {2019},
  editor = {Gao, Wen and Meng, Helen Mei{-}Ling and Turk, Matthew A. and Fussell, Susan R. and Schuller, Bj{\"{o}}rn W. and Song, Yale and Yu, Kai},
  pages = {521--525},
  publisher = {{ACM}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icmi/ZhuZZZ019.bib},
  doi = {10.1145/3340555.3356098},
  timestamp = {Fri, 03 Jul 2020 08:57:26 +0200},
  url = {https://doi.org/10.1145/3340555.3356098}
}

Robust Spoken Language Understanding with Acoustic and Domain Knowledge

Hao Li , Chen Liu , Su Zhu , and Kai Yu

In International Conference on Multimodal Interaction, ICMI 2019, Suzhou, China, October 14-18, 2019 , Oct 2019

Bib

@inproceedings{Li2019a,
  author = {Li, Hao and Liu, Chen and Zhu, Su and Yu, Kai},
  booktitle = {International Conference on Multimodal Interaction, {ICMI} 2019, Suzhou, China, October 14-18, 2019},
  title = {Robust Spoken Language Understanding with Acoustic and Domain Knowledge},
  year = {2019},
  editor = {Gao, Wen and Meng, Helen Mei{-}Ling and Turk, Matthew A. and Fussell, Susan R. and Schuller, Bj{\"{o}}rn W. and Song, Yale and Yu, Kai},
  pages = {531--535},
  publisher = {{ACM}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icmi/LiLZY19.bib},
  doi = {10.1145/3340555.3356100},
  timestamp = {Wed, 05 May 2021 01:00:00 +0200},
  url = {https://doi.org/10.1145/3340555.3356100}
}

Cross Aggregation of Multi-head Attention for Neural Machine Translation

Juncheng Cao , Hai Zhao , and Kai Yu

In Natural Language Processing and Chinese Computing - 8th CCF International Conference, NLPCC 2019, Dunhuang, China, October 9-14, 2019, Proceedings, Part I , Oct 2019

Bib

@inproceedings{Cao2019a,
  author = {Cao, Juncheng and Zhao, Hai and Yu, Kai},
  booktitle = {Natural Language Processing and Chinese Computing - 8th {CCF} International Conference, {NLPCC} 2019, Dunhuang, China, October 9-14, 2019, Proceedings, Part {I}},
  title = {Cross Aggregation of Multi-head Attention for Neural Machine Translation},
  year = {2019},
  editor = {Tang, Jie and Kan, Min{-}Yen and Zhao, Dongyan and Li, Sujian and Zan, Hongying},
  pages = {380--392},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  volume = {11838},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/nlpcc/CaoZY19.bib},
  doi = {10.1007/978-3-030-32233-5\_30},
  timestamp = {Sat, 18 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1007/978-3-030-32233-5\_30}
}

International Conference on Multimodal Interaction, ICMI 2019, Suzhou, China, October 14-18, 2019

Oct 2019

Bib

@proceedings{Gao2019,
  title = {International Conference on Multimodal Interaction, {ICMI} 2019, Suzhou, China, October 14-18, 2019},
  year = {2019},
  editor = {Gao, Wen and Meng, Helen Mei{-}Ling and Turk, Matthew A. and Fussell, Susan R. and Schuller, Bj{\"{o}}rn W. and Song, Yale and Yu, Kai},
  isbn = {978-1-4503-6860-5},
  publisher = {{ACM}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icmi/2019.bib},
  doi = {10.1145/3340555},
  timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
  url = {https://doi.org/10.1145/3340555}
}

2018

Past review, current progress, and challenges ahead on the cocktail party problem

Yanmin Qian , Chao Weng , Xuankai Chang , Shuai Wang , and Dong Yu

Frontiers Inf. Technol. Electron. Eng., Oct 2018

Bib

@article{Qian2018,
  author = {Qian, Yanmin and Weng, Chao and Chang, Xuankai and Wang, Shuai and Yu, Dong},
  journal = {Frontiers Inf. Technol. Electron. Eng.},
  title = {Past review, current progress, and challenges ahead on the cocktail party problem},
  year = {2018},
  number = {1},
  pages = {40--63},
  volume = {19},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/jzusc/QianWCWY18.bib},
  doi = {10.1631/FITEE.1700814},
  timestamp = {Thu, 05 Mar 2020 00:00:00 +0100},
  url = {https://doi.org/10.1631/FITEE.1700814}
}

Erratum to: Past review, current progress, and challenges ahead on the cocktail party problem

Yanmin Qian , Chao Weng , Xuankai Chang , Shuai Wang , and Dong Yu

Frontiers Inf. Technol. Electron. Eng., Oct 2018

Bib

@article{Qian2018a,
  author = {Qian, Yanmin and Weng, Chao and Chang, Xuankai and Wang, Shuai and Yu, Dong},
  journal = {Frontiers Inf. Technol. Electron. Eng.},
  title = {Erratum to: Past review, current progress, and challenges ahead on the cocktail party problem},
  year = {2018},
  number = {4},
  pages = {582},
  volume = {19},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/jzusc/QianWCWY18a.bib},
  doi = {10.1631/FITEE.17E0814},
  timestamp = {Thu, 05 Mar 2020 00:00:00 +0100},
  url = {https://doi.org/10.1631/FITEE.17e0814}
}

Sequence discriminative training for deep learning based acoustic keyword spotting

Zhehuai Chen , Yanmin Qian , and Kai Yu

Speech Commun., Oct 2018

Bib

@article{Chen2018,
  author = {Chen, Zhehuai and Qian, Yanmin and Yu, Kai},
  journal = {Speech Commun.},
  title = {Sequence discriminative training for deep learning based acoustic keyword spotting},
  year = {2018},
  pages = {100--111},
  volume = {102},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/speech/ChenQ018.bib},
  doi = {10.1016/J.SPECOM.2018.08.001},
  timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
  url = {https://doi.org/10.1016/j.specom.2018.08.001}
}

Single-channel multi-talker speech recognition with permutation invariant training

Yanmin Qian , Xuankai Chang , and Dong Yu

Speech Commun., Oct 2018

Bib

@article{Qian2018b,
  author = {Qian, Yanmin and Chang, Xuankai and Yu, Dong},
  journal = {Speech Commun.},
  title = {Single-channel multi-talker speech recognition with permutation invariant training},
  year = {2018},
  pages = {1--11},
  volume = {104},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/speech/QianCY18.bib},
  doi = {10.1016/J.SPECOM.2018.09.003},
  timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
  url = {https://doi.org/10.1016/j.specom.2018.09.003}
}

Adaptive Very Deep Convolutional Residual Network for Noise Robust Speech Recognition

Tian Tan , Yanmin Qian , Hu Hu , Ying Zhou , Wen Ding , and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2018

Bib

@article{Tan2018,
  author = {Tan, Tian and Qian, Yanmin and Hu, Hu and Zhou, Ying and Ding, Wen and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Adaptive Very Deep Convolutional Residual Network for Noise Robust Speech Recognition},
  year = {2018},
  number = {8},
  pages = {1393--1405},
  volume = {26},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/TanQHZDY18.bib},
  doi = {10.1109/TASLP.2018.2825432},
  timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2018.2825432}
}

Investigating Raw Wave Deep Neural Networks for End-to-End Speaker Spoofing Detection

Heinrich Dinkel , Yanmin Qian , and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2018

Bib

@article{Dinkel2018,
  author = {Dinkel, Heinrich and Qian, Yanmin and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Investigating Raw Wave Deep Neural Networks for End-to-End Speaker Spoofing Detection},
  year = {2018},
  number = {11},
  pages = {2002--2014},
  volume = {26},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/DinkelQY18.bib},
  doi = {10.1109/TASLP.2018.2851155},
  timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2018.2851155}
}

Robust Mask Estimation By Integrating Neural Network-Based and Clustering-Based Approaches for Adaptive Acoustic Beamforming

Ying Zhou , and Yanmin Qian

In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2018, Calgary, AB, Canada, April 15-20, 2018 , Oct 2018

Bib

@inproceedings{Zhou2018,
  author = {Zhou, Ying and Qian, Yanmin},
  booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  title = {Robust Mask Estimation By Integrating Neural Network-Based and Clustering-Based Approaches for Adaptive Acoustic Beamforming},
  year = {2018},
  pages = {536--540},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ZhouQ18.bib},
  doi = {10.1109/ICASSP.2018.8462462},
  timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
  url = {https://doi.org/10.1109/ICASSP.2018.8462462}
}

Knowledge Transfer in Permutation Invariant Training for Single-Channel Multi-Talker Speech Recognition

Tian Tan , Yanmin Qian , and Dong Yu

In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2018, Calgary, AB, Canada, April 15-20, 2018 , Oct 2018

Bib

@inproceedings{Tan2018a,
  author = {Tan, Tian and Qian, Yanmin and Yu, Dong},
  booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  title = {Knowledge Transfer in Permutation Invariant Training for Single-Channel Multi-Talker Speech Recognition},
  year = {2018},
  pages = {571--5718},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/0002Q018.bib},
  doi = {10.1109/ICASSP.2018.8461883},
  timestamp = {Tue, 18 Sep 2018 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2018.8461883}
}

Joint I-Vector with End-to-End System for Short Duration Text-Independent Speaker Verification

Zili Huang , Shuai Wang , and Yanmin Qian

In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2018, Calgary, AB, Canada, April 15-20, 2018 , Oct 2018

Bib

@inproceedings{Huang2018,
  author = {Huang, Zili and Wang, Shuai and Qian, Yanmin},
  booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  title = {Joint I-Vector with End-to-End System for Short Duration Text-Independent Speaker Verification},
  year = {2018},
  pages = {4869--4873},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/HuangWQ18.bib},
  doi = {10.1109/ICASSP.2018.8462508},
  timestamp = {Fri, 11 Oct 2019 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2018.8462508}
}

Generative Adversarial Networks Based Data Augmentation for Noise Robust Speech Recognition

Hu Hu , Tian Tan , and Yanmin Qian

In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2018, Calgary, AB, Canada, April 15-20, 2018 , Oct 2018

Bib

@inproceedings{Hu2018,
  author = {Hu, Hu and Tan, Tian and Qian, Yanmin},
  booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  title = {Generative Adversarial Networks Based Data Augmentation for Noise Robust Speech Recognition},
  year = {2018},
  pages = {5044--5048},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/Hu0Q18.bib},
  doi = {10.1109/ICASSP.2018.8462624},
  timestamp = {Tue, 18 Sep 2018 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2018.8462624}
}

Focal Kl-Divergence Based Dilated Convolutional Neural Networks for Co-Channel Speaker Identification

Shuai Wang , Yanmin Qian , and Kai Yu

In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2018, Calgary, AB, Canada, April 15-20, 2018 , Oct 2018

Bib

@inproceedings{Wang2018,
  author = {Wang, Shuai and Qian, Yanmin and Yu, Kai},
  booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  title = {Focal Kl-Divergence Based Dilated Convolutional Neural Networks for Co-Channel Speaker Identification},
  year = {2018},
  pages = {5339--5343},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/WangQ018.bib},
  doi = {10.1109/ICASSP.2018.8462620},
  timestamp = {Fri, 11 Oct 2019 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2018.8462620}
}

Noise Robust Speech Recognition on Aurora4 by Humans and Machines

Yanmin Qian , Tian Tan , Hu Hu , and Qi Liu

In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2018, Calgary, AB, Canada, April 15-20, 2018 , Oct 2018

Bib

@inproceedings{Qian2018c,
  author = {Qian, Yanmin and Tan, Tian and Hu, Hu and Liu, Qi},
  booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  title = {Noise Robust Speech Recognition on Aurora4 by Humans and Machines},
  year = {2018},
  pages = {5604--5608},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/Qian0HL18.bib},
  doi = {10.1109/ICASSP.2018.8462629},
  timestamp = {Wed, 18 May 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2018.8462629}
}

Fast Adaptation on Deepmixture Generative Network Based Acoustic Modeling

Wen Ding , Tian Tan , and Yanmin Qian

In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2018, Calgary, AB, Canada, April 15-20, 2018 , Oct 2018

Bib

@inproceedings{Ding2018,
  author = {Ding, Wen and Tan, Tian and Qian, Yanmin},
  booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  title = {Fast Adaptation on Deepmixture Generative Network Based Acoustic Modeling},
  year = {2018},
  pages = {5944--5948},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/Ding0Q18.bib},
  doi = {10.1109/ICASSP.2018.8462411},
  timestamp = {Tue, 18 Sep 2018 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2018.8462411}
}

Adaptive Permutation Invariant Training with Auxiliary Information for Monaural Multi-Talker Speech Recognition

Xuankai Chang , Yanmin Qian , and Dong Yu

In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2018, Calgary, AB, Canada, April 15-20, 2018 , Oct 2018

Bib

@inproceedings{Chang2018,
  author = {Chang, Xuankai and Qian, Yanmin and Yu, Dong},
  booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  title = {Adaptive Permutation Invariant Training with Auxiliary Information for Monaural Multi-Talker Speech Recognition},
  year = {2018},
  pages = {5974--5978},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ChangQY18.bib},
  doi = {10.1109/ICASSP.2018.8461570},
  timestamp = {Tue, 18 Sep 2018 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2018.8461570}
}

Permutation Invariant Training of Generative Adversarial Network for Monaural Speech Separation

Lianwu Chen , Meng Yu , Yanmin Qian , Dan Su , and Dong Yu

In Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018 , Oct 2018

Bib

@inproceedings{Chen2018a,
  author = {Chen, Lianwu and Yu, Meng and Qian, Yanmin and Su, Dan and Yu, Dong},
  booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018},
  title = {Permutation Invariant Training of Generative Adversarial Network for Monaural Speech Separation},
  year = {2018},
  editor = {Yegnanarayana, B.},
  pages = {302--306},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ChenYQSY18.bib},
  doi = {10.21437/INTERSPEECH.2018-1603},
  timestamp = {Fri, 21 May 2021 08:16:43 +0200},
  url = {https://doi.org/10.21437/Interspeech.2018-1603}
}

Deep Extractor Network for Target Speaker Recovery from Single Channel Speech Mixtures

Jun Wang , Jie Chen , Dan Su , Lianwu Chen , Meng Yu , Yanmin Qian , and Dong Yu

In Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018 , Oct 2018

Bib

@inproceedings{Wang2018a,
  author = {Wang, Jun and Chen, Jie and Su, Dan and Chen, Lianwu and Yu, Meng and Qian, Yanmin and Yu, Dong},
  booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018},
  title = {Deep Extractor Network for Target Speaker Recovery from Single Channel Speech Mixtures},
  year = {2018},
  editor = {Yegnanarayana, B.},
  pages = {307--311},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/WangCSCYQY18.bib},
  doi = {10.21437/INTERSPEECH.2018-1205},
  timestamp = {Wed, 22 Dec 2021 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2018-1205}
}

Monaural Multi-Talker Speech Recognition with Attention Mechanism and Gated Convolutional Networks

Xuankai Chang , Yanmin Qian , and Dong Yu

In Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018 , Oct 2018

Bib

@inproceedings{Chang2018a,
  author = {Chang, Xuankai and Qian, Yanmin and Yu, Dong},
  booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018},
  title = {Monaural Multi-Talker Speech Recognition with Attention Mechanism and Gated Convolutional Networks},
  year = {2018},
  editor = {Yegnanarayana, B.},
  pages = {1586--1590},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ChangQ018.bib},
  doi = {10.21437/INTERSPEECH.2018-1547},
  timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2018-1547}
}

Knowledge Distillation for Sequence Model

Mingkun Huang , Yongbin You , Zhehuai Chen , Yanmin Qian , and Kai Yu

In Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018 , Oct 2018

Bib

@inproceedings{Huang2018a,
  author = {Huang, Mingkun and You, Yongbin and Chen, Zhehuai and Qian, Yanmin and Yu, Kai},
  booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018},
  title = {Knowledge Distillation for Sequence Model},
  year = {2018},
  editor = {Yegnanarayana, B.},
  pages = {3703--3707},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/HuangYCQ018.bib},
  doi = {10.21437/INTERSPEECH.2018-1589},
  timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2018-1589}
}

Covariance Based Deep Feature for Text-Dependent Speaker Verification

Shuai Wang , Heinrich Dinkel , Yanmin Qian , and Kai Yu

In Intelligence Science and Big Data Engineering - 8th International Conference, IScIDE 2018, Lanzhou, China, August 18-19, 2018, Revised Selected Papers , Oct 2018

Bib

@inproceedings{Wang2018b,
  author = {Wang, Shuai and Dinkel, Heinrich and Qian, Yanmin and Yu, Kai},
  booktitle = {Intelligence Science and Big Data Engineering - 8th International Conference, IScIDE 2018, Lanzhou, China, August 18-19, 2018, Revised Selected Papers},
  title = {Covariance Based Deep Feature for Text-Dependent Speaker Verification},
  year = {2018},
  editor = {Peng, Yuxin and Yu, Kai and Lu, Jiwen and Jiang, Xingpeng},
  pages = {231--242},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  volume = {11266},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscide/WangDQ018.bib},
  doi = {10.1007/978-3-030-02698-1\_20},
  timestamp = {Fri, 11 Oct 2019 01:00:00 +0200},
  url = {https://doi.org/10.1007/978-3-030-02698-1\_20}
}

Data Augmentation using Conditional Generative Adversarial Networks for Robust Speech Recognition

Peiyao Sheng , Zhuolin Yang , Hu Hu , Tian Tan , and Yanmin Qian

In 11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018, Taipei City, Taiwan, November 26-29, 2018 , Oct 2018

Bib

@inproceedings{Sheng2018,
  author = {Sheng, Peiyao and Yang, Zhuolin and Hu, Hu and Tan, Tian and Qian, Yanmin},
  booktitle = {11th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2018, Taipei City, Taiwan, November 26-29, 2018},
  title = {Data Augmentation using Conditional Generative Adversarial Networks for Robust Speech Recognition},
  year = {2018},
  pages = {121--125},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/ShengYH0Q18.bib},
  doi = {10.1109/ISCSLP.2018.8706651},
  timestamp = {Wed, 16 Oct 2019 14:14:48 +0200},
  url = {https://doi.org/10.1109/ISCSLP.2018.8706651}
}

Deep Discriminant Analysis for i-vector Based Robust Speaker Recognition

Shuai Wang , Zili Huang , Yanmin Qian , and Kai Yu

In 11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018, Taipei City, Taiwan, November 26-29, 2018 , Oct 2018

Bib

@inproceedings{Wang2018c,
  author = {Wang, Shuai and Huang, Zili and Qian, Yanmin and Yu, Kai},
  booktitle = {11th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2018, Taipei City, Taiwan, November 26-29, 2018},
  title = {Deep Discriminant Analysis for i-vector Based Robust Speaker Recognition},
  year = {2018},
  pages = {195--199},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/WangHQ018.bib},
  doi = {10.1109/ISCSLP.2018.8706632},
  timestamp = {Fri, 11 Oct 2019 01:00:00 +0200},
  url = {https://doi.org/10.1109/ISCSLP.2018.8706632}
}

Generative Adversarial Networks based X-vector Augmentation for Robust Probabilistic Linear Discriminant Analysis in Speaker Verification

Yexin Yang , Shuai Wang , Man Sun , Yanmin Qian , and Kai Yu

In 11th International Symposium on Chinese Spoken Language Processing, ISCSLP 2018, Taipei City, Taiwan, November 26-29, 2018 , Oct 2018

Bib

@inproceedings{Yang2018,
  author = {Yang, Yexin and Wang, Shuai and Sun, Man and Qian, Yanmin and Yu, Kai},
  booktitle = {11th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2018, Taipei City, Taiwan, November 26-29, 2018},
  title = {Generative Adversarial Networks based X-vector Augmentation for Robust Probabilistic Linear Discriminant Analysis in Speaker Verification},
  year = {2018},
  pages = {205--209},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/YangWSQ018.bib},
  doi = {10.1109/ISCSLP.2018.8706575},
  timestamp = {Fri, 11 Oct 2019 01:00:00 +0200},
  url = {https://doi.org/10.1109/ISCSLP.2018.8706575}
}

Rich Short Text Conversation Using Semantic-Key-Controlled Sequence Generation

Kai Yu, Zijian Zhao , Xueyang Wu , Hongtao Lin , and Xuan Liu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2018

Bib

@article{Yu2018,
  author = {Yu, Kai and Zhao, Zijian and Wu, Xueyang and Lin, Hongtao and Liu, Xuan},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Rich Short Text Conversation Using Semantic-Key-Controlled Sequence Generation},
  year = {2018},
  number = {8},
  pages = {1359--1368},
  volume = {26},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/YuZWLL18.bib},
  doi = {10.1109/TASLP.2018.2819941},
  timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2018.2819941}
}

Structured Dialogue Policy with Graph Neural Networks

Lu Chen, Bowen Tan , Sishan Long , and Kai Yu

In Proceedings of the 27th International Conference on Computational Linguistics, COLING 2018, Santa Fe, New Mexico, USA, August 20-26, 2018 , Oct 2018

Bib

@inproceedings{Chen2018c,
  author = {Chen, Lu and Tan, Bowen and Long, Sishan and Yu, Kai},
  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics, {COLING} 2018, Santa Fe, New Mexico, USA, August 20-26, 2018},
  title = {Structured Dialogue Policy with Graph Neural Networks},
  year = {2018},
  editor = {Bender, Emily M. and Derczynski, Leon and Isabelle, Pierre},
  pages = {1257--1268},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/coling/ChenTLY18.bib},
  timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
  url = {https://aclanthology.org/C18-1107/}
}

Towards Universal Dialogue State Tracking

Liliang Ren , Kaige Xie , Lu Chen, and Kai Yu

In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, October 31 - November 4, 2018 , Oct 2018

Bib

@inproceedings{Ren2018,
  author = {Ren, Liliang and Xie, Kaige and Chen, Lu and Yu, Kai},
  booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, October 31 - November 4, 2018},
  title = {Towards Universal Dialogue State Tracking},
  year = {2018},
  editor = {Riloff, Ellen and Chiang, David and Hockenmaier, Julia and Tsujii, Jun'ichi},
  pages = {2780--2786},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/emnlp/RenXCY18.bib},
  doi = {10.18653/V1/D18-1299},
  timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/d18-1299}
}

On Modular Training of Neural Acoustics-to-Word Model for LVCSR

Zhehuai Chen , Qi Liu , Hao Li , and Kai Yu

In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2018, Calgary, AB, Canada, April 15-20, 2018 , Oct 2018

Bib

@inproceedings{Chen2018d,
  author = {Chen, Zhehuai and Liu, Qi and Li, Hao and Yu, Kai},
  booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  title = {On Modular Training of Neural Acoustics-to-Word Model for {LVCSR}},
  year = {2018},
  pages = {4754--4758},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ChenLLY18.bib},
  doi = {10.1109/ICASSP.2018.8461361},
  timestamp = {Wed, 18 May 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2018.8461361}
}

Semi-Supervised Training Using Adversarial Multi-Task Learning for Spoken Language Understanding

Ouyu Lan , Su Zhu , and Kai Yu

In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2018, Calgary, AB, Canada, April 15-20, 2018 , Oct 2018

Bib

@inproceedings{Lan2018,
  author = {Lan, Ouyu and Zhu, Su and Yu, Kai},
  booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  title = {Semi-Supervised Training Using Adversarial Multi-Task Learning for Spoken Language Understanding},
  year = {2018},
  pages = {6049--6053},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/LanZY18.bib},
  doi = {10.1109/ICASSP.2018.8462669},
  timestamp = {Fri, 18 Oct 2019 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2018.8462669}
}

Policy Adaptation for Deep Reinforcement Learning-Based Dialogue Management

Lu Chen, Cheng Chang , Zhi Chen , Bowen Tan , Milica Gasic , and Kai Yu

In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2018, Calgary, AB, Canada, April 15-20, 2018 , Oct 2018

Bib

@inproceedings{Chen2018e,
  author = {Chen, Lu and Chang, Cheng and Chen, Zhi and Tan, Bowen and Gasic, Milica and Yu, Kai},
  booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  title = {Policy Adaptation for Deep Reinforcement Learning-Based Dialogue Management},
  year = {2018},
  pages = {6074--6078},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ChenCCTGY18.bib},
  doi = {10.1109/ICASSP.2018.8462272},
  timestamp = {Fri, 27 Sep 2019 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2018.8462272}
}

Robust Spoken Language Understanding with Unsupervised ASR-Error Adaptation

Su Zhu , Ouyu Lan , and Kai Yu

In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2018, Calgary, AB, Canada, April 15-20, 2018 , Oct 2018

Bib

@inproceedings{Zhu2018,
  author = {Zhu, Su and Lan, Ouyu and Yu, Kai},
  booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  title = {Robust Spoken Language Understanding with Unsupervised ASR-Error Adaptation},
  year = {2018},
  pages = {6179--6183},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ZhuLY18.bib},
  doi = {10.1109/ICASSP.2018.8461831},
  timestamp = {Fri, 18 Oct 2019 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2018.8461831}
}

MLN: Moment localization Network and Samples Selection for Moment Retrieval

Bo Huang , Ya Zhang , and Kai Yu

In Proceedings of the 2nd International Conference on Video and Image Processing, ICVIP 2018, Hong Kong, China, December 29-31, 2018 , Oct 2018

Bib

@inproceedings{Huang2018b,
  author = {Huang, Bo and Zhang, Ya and Yu, Kai},
  booktitle = {Proceedings of the 2nd International Conference on Video and Image Processing, {ICVIP} 2018, Hong Kong, China, December 29-31, 2018},
  title = {{MLN:} Moment localization Network and Samples Selection for Moment Retrieval},
  year = {2018},
  pages = {165--170},
  publisher = {{ACM}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icvip/HuangZ018.bib},
  doi = {10.1145/3301506.3301538},
  timestamp = {Fri, 28 Apr 2023 01:00:00 +0200},
  url = {https://doi.org/10.1145/3301506.3301538}
}

Angular Softmax for Short-Duration Text-independent Speaker Verification

Zili Huang , Shuai Wang , and Kai Yu

In Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018 , Oct 2018

Bib

@inproceedings{Huang2018c,
  author = {Huang, Zili and Wang, Shuai and Yu, Kai},
  booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018},
  title = {Angular Softmax for Short-Duration Text-independent Speaker Verification},
  year = {2018},
  editor = {Yegnanarayana, B.},
  pages = {3623--3627},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/HuangW018.bib},
  doi = {10.21437/INTERSPEECH.2018-1545},
  timestamp = {Fri, 21 May 2021 08:16:43 +0200},
  url = {https://doi.org/10.21437/Interspeech.2018-1545}
}

Joint Spoken Language Understanding and Domain Adaptive Language Modeling

Huifeng Zhang , Su Zhu , Shuai Fan , and Kai Yu

In Intelligence Science and Big Data Engineering - 8th International Conference, IScIDE 2018, Lanzhou, China, August 18-19, 2018, Revised Selected Papers , Oct 2018

Bib

@inproceedings{Zhang2018,
  author = {Zhang, Huifeng and Zhu, Su and Fan, Shuai and Yu, Kai},
  booktitle = {Intelligence Science and Big Data Engineering - 8th International Conference, IScIDE 2018, Lanzhou, China, August 18-19, 2018, Revised Selected Papers},
  title = {Joint Spoken Language Understanding and Domain Adaptive Language Modeling},
  year = {2018},
  editor = {Peng, Yuxin and Yu, Kai and Lu, Jiwen and Jiang, Xingpeng},
  pages = {311--324},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  volume = {11266},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscide/ZhangZF018.bib},
  doi = {10.1007/978-3-030-02698-1\_27},
  timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
  url = {https://doi.org/10.1007/978-3-030-02698-1\_27}
}

Binarized LSTM Language Model

Xuan Liu , Di Cao , and Kai Yu

In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, June 1-6, 2018, Volume 1 (Long Papers) , Oct 2018

Bib

@inproceedings{Liu2018,
  author = {Liu, Xuan and Cao, Di and Yu, Kai},
  booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, {NAACL-HLT} 2018, New Orleans, Louisiana, USA, June 1-6, 2018, Volume 1 (Long Papers)},
  title = {Binarized {LSTM} Language Model},
  year = {2018},
  editor = {Walker, Marilyn A. and Ji, Heng and Stent, Amanda},
  pages = {2113--2121},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/naacl/LiuCY18.bib},
  doi = {10.18653/V1/N18-1192},
  timestamp = {Wed, 01 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/n18-1192}
}

Cost-Sensitive Active Learning for Dialogue State Tracking

Kaige Xie , Cheng Chang , Liliang Ren , Lu Chen, and Kai Yu

In Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, Melbourne, Australia, July 12-14, 2018 , Oct 2018

Bib

@inproceedings{Xie2018,
  author = {Xie, Kaige and Chang, Cheng and Ren, Liliang and Chen, Lu and Yu, Kai},
  booktitle = {Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, Melbourne, Australia, July 12-14, 2018},
  title = {Cost-Sensitive Active Learning for Dialogue State Tracking},
  year = {2018},
  editor = {Komatani, Kazunori and Litman, Diane J. and Yu, Kai and Cavedon, Lawrence and Nakano, Mikio and Papangelis, Alex},
  pages = {209--213},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/sigdial/XieCRCY18.bib},
  doi = {10.18653/V1/W18-5022},
  timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/w18-5022}
}

Concept Transfer Learning for Adaptive Language Understanding

Su Zhu , and Kai Yu

In Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, Melbourne, Australia, July 12-14, 2018 , Oct 2018

Bib

@inproceedings{Zhu2018a,
  author = {Zhu, Su and Yu, Kai},
  booktitle = {Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, Melbourne, Australia, July 12-14, 2018},
  title = {Concept Transfer Learning for Adaptive Language Understanding},
  year = {2018},
  editor = {Komatani, Kazunori and Litman, Diane J. and Yu, Kai and Cavedon, Lawrence and Nakano, Mikio and Papangelis, Alex},
  pages = {391--399},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/sigdial/ZhuY18.bib},
  doi = {10.18653/V1/W18-5047},
  timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/w18-5047}
}

Intelligence Science and Big Data Engineering - 8th International Conference, IScIDE 2018, Lanzhou, China, August 18-19, 2018, Revised Selected Papers

Oct 2018

Bib

@proceedings{Peng2018,
  title = {Intelligence Science and Big Data Engineering - 8th International Conference, IScIDE 2018, Lanzhou, China, August 18-19, 2018, Revised Selected Papers},
  year = {2018},
  editor = {Peng, Yuxin and Yu, Kai and Lu, Jiwen and Jiang, Xingpeng},
  isbn = {978-3-030-02697-4},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  volume = {11266},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscide/2018.bib},
  doi = {10.1007/978-3-030-02698-1},
  timestamp = {Tue, 14 May 2019 01:00:00 +0200},
  url = {https://doi.org/10.1007/978-3-030-02698-1}
}

2017

Phone Synchronous Speech Recognition With CTC Lattices

Zhehuai Chen , Yimeng Zhuang , Yanmin Qian , and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2017

Bib

@article{Chen2017,
  author = {Chen, Zhehuai and Zhuang, Yimeng and Qian, Yanmin and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Phone Synchronous Speech Recognition With {CTC} Lattices},
  year = {2017},
  number = {1},
  pages = {86--97},
  volume = {25},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/ChenZQY17.bib},
  doi = {10.1109/TASLP.2016.2625459},
  timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2016.2625459}
}

Deep Feature Engineering for Noise Robust Spoofing Detection

Yanmin Qian , Nanxin Chen , Heinrich Dinkel , and Zhizheng Wu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2017

Bib

@article{Qian2017,
  author = {Qian, Yanmin and Chen, Nanxin and Dinkel, Heinrich and Wu, Zhizheng},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Deep Feature Engineering for Noise Robust Spoofing Detection},
  year = {2017},
  number = {10},
  pages = {1942--1955},
  volume = {25},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/QianCDW17.bib},
  doi = {10.1109/TASLP.2017.2732162},
  timestamp = {Sat, 18 Feb 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2017.2732162}
}

Integrating online i-vector into GMM-UBM for text-dependent speaker verification

Xiaowei Jiang , Shuai Wang , Xu Xiang , and Yanmin Qian

In 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017, Kuala Lumpur, Malaysia, December 12-15, 2017 , Oct 2017

Bib

@inproceedings{Jiang2017,
  author = {Jiang, Xiaowei and Wang, Shuai and Xiang, Xu and Qian, Yanmin},
  booktitle = {2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2017, Kuala Lumpur, Malaysia, December 12-15, 2017},
  title = {Integrating online i-vector into {GMM-UBM} for text-dependent speaker verification},
  year = {2017},
  pages = {1628--1632},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/apsipa/JiangWXQ17.bib},
  doi = {10.1109/APSIPA.2017.8282293},
  timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/APSIPA.2017.8282293}
}

Future vector enhanced LSTM language model for LVCSR

Qi Liu , Yanmin Qian , and Kai Yu

In 2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017, Okinawa, Japan, December 16-20, 2017 , Oct 2017

Bib

@inproceedings{Liu2017,
  author = {Liu, Qi and Qian, Yanmin and Yu, Kai},
  booktitle = {2017 {IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU} 2017, Okinawa, Japan, December 16-20, 2017},
  title = {Future vector enhanced {LSTM} language model for {LVCSR}},
  year = {2017},
  pages = {104--110},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/asru/LiuQ017.bib},
  doi = {10.1109/ASRU.2017.8268923},
  timestamp = {Wed, 18 May 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ASRU.2017.8268923}
}

Multi-view LSTM Language Model with Word-Synchronized Auxiliary Feature for LVCSR

Yue Wu , Tianxing He , Zhehuai Chen , Yanmin Qian , and Kai Yu

In Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data - 16th China National Conference, CCL 2017, - and - 5th International Symposium, NLP-NABD 2017, Nanjing, China, October 13-15, 2017, Proceedings , Oct 2017

Bib

@inproceedings{Wu2017,
  author = {Wu, Yue and He, Tianxing and Chen, Zhehuai and Qian, Yanmin and Yu, Kai},
  booktitle = {Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data - 16th China National Conference, {CCL} 2017, - and - 5th International Symposium, {NLP-NABD} 2017, Nanjing, China, October 13-15, 2017, Proceedings},
  title = {Multi-view {LSTM} Language Model with Word-Synchronized Auxiliary Feature for {LVCSR}},
  year = {2017},
  editor = {Sun, Maosong and Wang, Xiaojie and Chang, Baobao and Xiong, Deyi},
  pages = {398--410},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  volume = {10565},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/cncl/WuHCQY17.bib},
  doi = {10.1007/978-3-319-69005-6\_33},
  timestamp = {Fri, 01 Sep 2023 13:50:17 +0200},
  url = {https://doi.org/10.1007/978-3-319-69005-6\_33}
}

End-to-end spoofing detection with raw waveform CLDNNS

Heinrich Dinkel , Nanxin Chen , Yanmin Qian , and Kai Yu

In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2017, New Orleans, LA, USA, March 5-9, 2017 , Oct 2017

Bib

@inproceedings{Dinkel2017,
  author = {Dinkel, Heinrich and Chen, Nanxin and Qian, Yanmin and Yu, Kai},
  booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
  title = {End-to-end spoofing detection with raw waveform {CLDNNS}},
  year = {2017},
  pages = {4860--4864},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/DinkelCQY17.bib},
  doi = {10.1109/ICASSP.2017.7953080},
  timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
  url = {https://doi.org/10.1109/ICASSP.2017.7953080}
}

Small-footprint convolutional neural network for spoofing detection

Heinrich Dinkel , Yanmin Qian , and Kai Yu

In 2017 International Joint Conference on Neural Networks, IJCNN 2017, Anchorage, AK, USA, May 14-19, 2017 , Oct 2017

Bib

@inproceedings{Dinkel2017a,
  author = {Dinkel, Heinrich and Qian, Yanmin and Yu, Kai},
  booktitle = {2017 International Joint Conference on Neural Networks, {IJCNN} 2017, Anchorage, AK, USA, May 14-19, 2017},
  title = {Small-footprint convolutional neural network for spoofing detection},
  year = {2017},
  pages = {3086--3091},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/ijcnn/DinkelQY17.bib},
  doi = {10.1109/IJCNN.2017.7966240},
  timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
  url = {https://doi.org/10.1109/IJCNN.2017.7966240}
}

Binary Deep Neural Networks for Speech Recognition

Xu Xiang , Yanmin Qian , and Kai Yu

In Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017 , Oct 2017

Bib

@inproceedings{Xiang2017,
  author = {Xiang, Xu and Qian, Yanmin and Yu, Kai},
  booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017},
  title = {Binary Deep Neural Networks for Speech Recognition},
  year = {2017},
  editor = {Lacerda, Francisco},
  pages = {533--537},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/XiangQ017.bib},
  doi = {10.21437/INTERSPEECH.2017-1343},
  timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2017-1343}
}

What Does the Speaker Embedding Encode?

Shuai Wang , Yanmin Qian , and Kai Yu

In Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017 , Oct 2017

Bib

@inproceedings{Wang2017,
  author = {Wang, Shuai and Qian, Yanmin and Yu, Kai},
  booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017},
  title = {What Does the Speaker Embedding Encode?},
  year = {2017},
  editor = {Lacerda, Francisco},
  pages = {1497--1501},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/WangQ017.bib},
  doi = {10.21437/INTERSPEECH.2017-1125},
  timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2017-1125}
}

Recognizing Multi-Talker Speech with Permutation Invariant Training

Dong Yu , Xuankai Chang , and Yanmin Qian

In Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017 , Oct 2017

Bib

@inproceedings{Yu2017,
  author = {Yu, Dong and Chang, Xuankai and Qian, Yanmin},
  booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017},
  title = {Recognizing Multi-Talker Speech with Permutation Invariant Training},
  year = {2017},
  editor = {Lacerda, Francisco},
  pages = {2456--2460},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/YuCQ17.bib},
  doi = {10.21437/INTERSPEECH.2017-305},
  timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2017-305}
}

A Unified Confidence Measure Framework Using Auxiliary Normalization Graph

Zhehuai Chen , Yanmin Qian , and Kai Yu

In Intelligence Science and Big Data Engineering - 7th International Conference, IScIDE 2017, Dalian, China, September 22-23, 2017, Proceedings , Oct 2017

Bib

@inproceedings{Chen2017a,
  author = {Chen, Zhehuai and Qian, Yanmin and Yu, Kai},
  booktitle = {Intelligence Science and Big Data Engineering - 7th International Conference, IScIDE 2017, Dalian, China, September 22-23, 2017, Proceedings},
  title = {A Unified Confidence Measure Framework Using Auxiliary Normalization Graph},
  year = {2017},
  editor = {Sun, Yi and Lu, Huchuan and Zhang, Lihe and Yang, Jian and Huang, Hua},
  pages = {123--133},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  volume = {10559},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscide/ChenQY17.bib},
  doi = {10.1007/978-3-319-67777-4\_11},
  timestamp = {Tue, 14 May 2019 10:00:39 +0200},
  url = {https://doi.org/10.1007/978-3-319-67777-4\_11}
}

Adaptation of Deep Neural Network Acoustic Models for Robust Automatic Speech Recognition

Khe Chai Sim , Yanmin Qian , Gautam Mantena , Lahiru Samarakoon , Souvik Kundu , and Tian Tan

In New Era for Robust Speech Recognition, Exploiting Deep Learning , Oct 2017

Bib

@incollection{Sim2017,
  author = {Sim, Khe Chai and Qian, Yanmin and Mantena, Gautam and Samarakoon, Lahiru and Kundu, Souvik and Tan, Tian},
  booktitle = {New Era for Robust Speech Recognition, Exploiting Deep Learning},
  publisher = {Springer},
  title = {Adaptation of Deep Neural Network Acoustic Models for Robust Automatic Speech Recognition},
  year = {2017},
  editor = {Watanabe, Shinji and Delcroix, Marc and Metze, Florian and Hershey, John R.},
  pages = {219--243},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/books/sp/17/SimQMSKT17.bib},
  doi = {10.1007/978-3-319-64680-0\_9},
  timestamp = {Wed, 23 Jun 2021 01:00:00 +0200},
  url = {https://doi.org/10.1007/978-3-319-64680-0\_9}
}

On-line Dialogue Policy Learning with Companion Teaching

Lu Chen, Runzhe Yang , Cheng Chang , Zihao Ye , Xiang Zhou , and Kai Yu

In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017, Valencia, Spain, April 3-7, 2017, Volume 2: Short Papers , Oct 2017

Bib

@inproceedings{Chen2017b,
  author = {Chen, Lu and Yang, Runzhe and Chang, Cheng and Ye, Zihao and Zhou, Xiang and Yu, Kai},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, {EACL} 2017, Valencia, Spain, April 3-7, 2017, Volume 2: Short Papers},
  title = {On-line Dialogue Policy Learning with Companion Teaching},
  year = {2017},
  editor = {Lapata, Mirella and Blunsom, Phil and Koller, Alexander},
  pages = {198--204},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/eacl/ChenYCYZY17.bib},
  doi = {10.18653/V1/E17-2032},
  timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/e17-2032}
}

Affordable On-line Dialogue Policy Learning

Cheng Chang , Runzhe Yang , Lu Chen, Xiang Zhou , and Kai Yu

In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, September 9-11, 2017 , Oct 2017

Bib

@inproceedings{Chang2017,
  author = {Chang, Cheng and Yang, Runzhe and Chen, Lu and Zhou, Xiang and Yu, Kai},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, {EMNLP} 2017, Copenhagen, Denmark, September 9-11, 2017},
  title = {Affordable On-line Dialogue Policy Learning},
  year = {2017},
  editor = {Palmer, Martha and Hwa, Rebecca and Riedel, Sebastian},
  pages = {2200--2209},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/emnlp/ChangYCZY17.bib},
  doi = {10.18653/V1/D17-1234},
  timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/d17-1234}
}

Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning

Lu Chen, Xiang Zhou , Cheng Chang , Runzhe Yang , and Kai Yu

In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, September 9-11, 2017 , Oct 2017

Bib

@inproceedings{Chen2017c,
  author = {Chen, Lu and Zhou, Xiang and Chang, Cheng and Yang, Runzhe and Yu, Kai},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, {EMNLP} 2017, Copenhagen, Denmark, September 9-11, 2017},
  title = {Agent-Aware Dropout {DQN} for Safe and Efficient On-line Dialogue Policy Learning},
  year = {2017},
  editor = {Palmer, Martha and Hwa, Rebecca and Riedel, Sebastian},
  pages = {2454--2464},
  publisher = {Association for Computational Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/emnlp/ChenZCYY17.bib},
  doi = {10.18653/V1/D17-1260},
  timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/d17-1260}
}

Confidence measures for CTC-based phone synchronous decoding

Zhehuai Chen , Yimeng Zhuang , and Kai Yu

In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2017, New Orleans, LA, USA, March 5-9, 2017 , Oct 2017

Bib

@inproceedings{Chen2017d,
  author = {Chen, Zhehuai and Zhuang, Yimeng and Yu, Kai},
  booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
  title = {Confidence measures for CTC-based phone synchronous decoding},
  year = {2017},
  pages = {4850--4854},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ChenZY17.bib},
  doi = {10.1109/ICASSP.2017.7953078},
  timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
  url = {https://doi.org/10.1109/ICASSP.2017.7953078}
}

Encoder-decoder with focus-mechanism for sequence labelling based spoken language understanding

Su Zhu , and Kai Yu

In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2017, New Orleans, LA, USA, March 5-9, 2017 , Oct 2017

Bib

@inproceedings{Zhu2017,
  author = {Zhu, Su and Yu, Kai},
  booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
  title = {Encoder-decoder with focus-mechanism for sequence labelling based spoken language understanding},
  year = {2017},
  pages = {5675--5679},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/ZhuY17.bib},
  doi = {10.1109/ICASSP.2017.7953243},
  timestamp = {Fri, 18 Oct 2019 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2017.7953243}
}

Discrete Duration Model for Speech Synthesis

Bo Chen , Tianling Bian , and Kai Yu

In Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017 , Oct 2017

Bib

@inproceedings{Chen2017e,
  author = {Chen, Bo and Bian, Tianling and Yu, Kai},
  booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017},
  title = {Discrete Duration Model for Speech Synthesis},
  year = {2017},
  editor = {Lacerda, Francisco},
  pages = {789--793},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ChenB017.bib},
  doi = {10.21437/INTERSPEECH.2017-1144},
  timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2017-1144}
}

Deep Attentive Structured Language Model Based on LSTM

Di Cao , and Kai Yu

In Intelligence Science and Big Data Engineering - 7th International Conference, IScIDE 2017, Dalian, China, September 22-23, 2017, Proceedings , Oct 2017

Bib

@inproceedings{Cao2017,
  author = {Cao, Di and Yu, Kai},
  booktitle = {Intelligence Science and Big Data Engineering - 7th International Conference, IScIDE 2017, Dalian, China, September 22-23, 2017, Proceedings},
  title = {Deep Attentive Structured Language Model Based on {LSTM}},
  year = {2017},
  editor = {Sun, Yi and Lu, Huchuan and Zhang, Lihe and Yang, Jian and Huang, Hua},
  pages = {169--180},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  volume = {10559},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscide/CaoY17.bib},
  doi = {10.1007/978-3-319-67777-4\_15},
  timestamp = {Wed, 01 Jun 2022 01:00:00 +0200},
  url = {https://doi.org/10.1007/978-3-319-67777-4\_15}
}

splab at the NTCIR-13 STC-2 Task

Xuan Liu , Xueyang Wu , Ruinian Chen , Zijian Zhao , Hongtao Lin , and Kai Yu

In The 13th NTCIR Conference, Evaluation of Information Access Technologies, National Center of Sciences, Tokyo, Japan, December 5-8, 2017 , Oct 2017

Bib

@inproceedings{Liu2017a,
  author = {Liu, Xuan and Wu, Xueyang and Chen, Ruinian and Zhao, Zijian and Lin, Hongtao and Yu, Kai},
  booktitle = {The 13th {NTCIR} Conference, Evaluation of Information Access Technologies, National Center of Sciences, Tokyo, Japan, December 5-8, 2017},
  title = {splab at the {NTCIR-13} {STC-2} Task},
  year = {2017},
  publisher = {National Institute of Informatics {(NII)}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/ntcir/Liu0CZL017.bib},
  timestamp = {Wed, 01 Jun 2022 17:01:01 +0200},
  url = {https://research.nii.ac.jp/ntcir/workshop/OnlineProceedings13/pdf/ntcir/21-NTCIR13-STC-LiuX.pdf}
}

2016

Deep features for automatic spoofing detection

Yanmin Qian , Nanxin Chen , and Kai Yu

Speech Commun., Oct 2016

Bib

@article{Qian2016,
  author = {Qian, Yanmin and Chen, Nanxin and Yu, Kai},
  journal = {Speech Commun.},
  title = {Deep features for automatic spoofing detection},
  year = {2016},
  pages = {43--52},
  volume = {85},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/speech/QianCY16.bib},
  doi = {10.1016/J.SPECOM.2016.10.007},
  timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
  url = {https://doi.org/10.1016/j.specom.2016.10.007}
}

Cluster Adaptive Training for Deep Neural Network Based Acoustic Model

Tian Tan , Yanmin Qian , and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2016

Bib

@article{Tan2016,
  author = {Tan, Tian and Qian, Yanmin and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Cluster Adaptive Training for Deep Neural Network Based Acoustic Model},
  year = {2016},
  number = {3},
  pages = {459--468},
  volume = {24},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/TanQY16.bib},
  doi = {10.1109/TASLP.2015.2511922},
  timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2015.2511922}
}

Neural Network Based Multi-Factor Aware Joint Training for Robust Speech Recognition

Yanmin Qian , Tian Tan , and Dong Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2016

Bib

@article{Qian2016a,
  author = {Qian, Yanmin and Tan, Tian and Yu, Dong},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Neural Network Based Multi-Factor Aware Joint Training for Robust Speech Recognition},
  year = {2016},
  number = {12},
  pages = {2231--2240},
  volume = {24},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/QianTY16.bib},
  doi = {10.1109/TASLP.2016.2598308},
  timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2016.2598308}
}

Very Deep Convolutional Neural Networks for Noise Robust Speech Recognition

Yanmin Qian , Mengxiao Bi , Tian Tan , and Kai Yu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2016

Bib

@article{Qian2016b,
  author = {Qian, Yanmin and Bi, Mengxiao and Tan, Tian and Yu, Kai},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Very Deep Convolutional Neural Networks for Noise Robust Speech Recognition},
  year = {2016},
  number = {12},
  pages = {2263--2276},
  volume = {24},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/QianBTY16.bib},
  doi = {10.1109/TASLP.2016.2602884},
  timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
  url = {https://doi.org/10.1109/TASLP.2016.2602884}
}

Overview of BTAS 2016 speaker anti-spoofing competition

Pavel Korshunov , Sébastien Marcel , Hannah Muckenhirn , André R. Gonçalves , A. G. Souza Mello , Ricardo Paranhos Velloso Violato , Flávio Olmos Simões , M. U. Neto , Marcus Assis Angeloni , José Augusto Stuchi , Heinrich Dinkel , Nanxin Chen , Yanmin Qian , Dipjyoti Paul , Goutam Saha , and Md. Sahidullah

In 8th IEEE International Conference on Biometrics Theory, Applications and Systems, BTAS 2016, Niagara Falls, NY, USA, September 6-9, 2016 , Oct 2016

Bib

@inproceedings{Korshunov2016,
  author = {Korshunov, Pavel and Marcel, S{\'{e}}bastien and Muckenhirn, Hannah and Gon{\c{c}}alves, Andr{\'{e}} R. and Mello, A. G. Souza and Violato, Ricardo Paranhos Velloso and Sim{\~{o}}es, Fl{\'{a}}vio Olmos and Neto, M. U. and de Assis Angeloni, Marcus and Stuchi, Jos{\'{e}} Augusto and Dinkel, Heinrich and Chen, Nanxin and Qian, Yanmin and Paul, Dipjyoti and Saha, Goutam and Sahidullah, Md.},
  booktitle = {8th {IEEE} International Conference on Biometrics Theory, Applications and Systems, {BTAS} 2016, Niagara Falls, NY, USA, September 6-9, 2016},
  title = {Overview of {BTAS} 2016 speaker anti-spoofing competition},
  year = {2016},
  pages = {1--6},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/btas/KorshunovMMGMVS16.bib},
  doi = {10.1109/BTAS.2016.7791200},
  timestamp = {Tue, 22 Nov 2022 00:00:00 +0100},
  url = {https://doi.org/10.1109/BTAS.2016.7791200}
}

Joint acoustic factor learning for robust deep neural network based automatic speech recognition

Souvik Kundu , Gautam Mantena , Yanmin Qian , Tian Tan , Marc Delcroix , and Khe Chai Sim

In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, March 20-25, 2016 , Oct 2016

Bib

@inproceedings{Kundu2016,
  author = {Kundu, Souvik and Mantena, Gautam and Qian, Yanmin and Tan, Tian and Delcroix, Marc and Sim, Khe Chai},
  booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
  title = {Joint acoustic factor learning for robust deep neural network based automatic speech recognition},
  year = {2016},
  pages = {5025--5029},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/KunduMQTDS16.bib},
  doi = {10.1109/ICASSP.2016.7472634},
  timestamp = {Wed, 23 Jun 2021 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2016.7472634}
}

Speaker-aware training of LSTM-RNNS for acoustic modelling

Tian Tan , Yanmin Qian , Dong Yu , Souvik Kundu , Liang Lu , Khe Chai Sim , Xiong Xiao , and Yu Zhang

In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, March 20-25, 2016 , Oct 2016

Bib

@inproceedings{Tan2016a,
  author = {Tan, Tian and Qian, Yanmin and Yu, Dong and Kundu, Souvik and Lu, Liang and Sim, Khe Chai and Xiao, Xiong and Zhang, Yu},
  booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
  title = {Speaker-aware training of {LSTM-RNNS} for acoustic modelling},
  year = {2016},
  pages = {5280--5284},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/TanQYKLSXZ16.bib},
  doi = {10.1109/ICASSP.2016.7472685},
  timestamp = {Sat, 31 Jul 2021 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2016.7472685}
}

Improved DNN-based segmentation for multi-genre broadcast audio

Linlin Wang , Chao Zhang , Philip C. Woodland , Mark J. F. Gales , Panagiota Karanasou , Pierre Lanchantin , Xunying Liu , and Yanmin Qian

In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, March 20-25, 2016 , Oct 2016

Bib

@inproceedings{Wang2016,
  author = {Wang, Linlin and Zhang, Chao and Woodland, Philip C. and Gales, Mark J. F. and Karanasou, Panagiota and Lanchantin, Pierre and Liu, Xunying and Qian, Yanmin},
  booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
  title = {Improved DNN-based segmentation for multi-genre broadcast audio},
  year = {2016},
  pages = {5700--5704},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/WangZWGKLLQ16.bib},
  doi = {10.1109/ICASSP.2016.7472769},
  timestamp = {Tue, 23 Jun 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2016.7472769}
}

An investigation into using parallel data for far-field speech recognition

Yanmin Qian , Tian Tan , and Dong Yu

In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, March 20-25, 2016 , Oct 2016

Bib

@inproceedings{Qian2016c,
  author = {Qian, Yanmin and Tan, Tian and Yu, Dong},
  booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
  title = {An investigation into using parallel data for far-field speech recognition},
  year = {2016},
  pages = {5725--5729},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/QianTY16.bib},
  doi = {10.1109/ICASSP.2016.7472774},
  timestamp = {Mon, 16 Jul 2018 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2016.7472774}
}

Integrated adaptation with multi-factor joint-learning for far-field speech recognition

Yanmin Qian , Tian Tan , Dong Yu , and Yu Zhang

In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, March 20-25, 2016 , Oct 2016

Bib

@inproceedings{Qian2016d,
  author = {Qian, Yanmin and Tan, Tian and Yu, Dong and Zhang, Yu},
  booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
  title = {Integrated adaptation with multi-factor joint-learning for far-field speech recognition},
  year = {2016},
  pages = {5770--5774},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/QianTYZ16.bib},
  doi = {10.1109/ICASSP.2016.7472783},
  timestamp = {Mon, 16 Jul 2018 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2016.7472783}
}

Unrestricted Vocabulary Keyword Spotting Using LSTM-CTC

Yimeng Zhuang , Xuankai Chang , Yanmin Qian , and Kai Yu

In Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016 , Oct 2016

Bib

@inproceedings{Zhuang2016,
  author = {Zhuang, Yimeng and Chang, Xuankai and Qian, Yanmin and Yu, Kai},
  booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016},
  title = {Unrestricted Vocabulary Keyword Spotting Using {LSTM-CTC}},
  year = {2016},
  editor = {Morgan, Nelson},
  pages = {938--942},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ZhuangCQY16.bib},
  doi = {10.21437/INTERSPEECH.2016-753},
  timestamp = {Mon, 26 Jun 2023 16:43:56 +0200},
  url = {https://doi.org/10.21437/Interspeech.2016-753}
}

Multi-task joint-learning for robust voice activity detection

Yimeng Zhuang , Sibo Tong , Maofan Yin , Yanmin Qian , and Kai Yu

In 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016, Tianjin, China, October 17-20, 2016 , Oct 2016

Bib

@inproceedings{Zhuang2016a,
  author = {Zhuang, Yimeng and Tong, Sibo and Yin, Maofan and Qian, Yanmin and Yu, Kai},
  booktitle = {10th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2016, Tianjin, China, October 17-20, 2016},
  title = {Multi-task joint-learning for robust voice activity detection},
  year = {2016},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/ZhuangTYQY16.bib},
  doi = {10.1109/ISCSLP.2016.7918383},
  timestamp = {Wed, 16 Oct 2019 14:14:48 +0200},
  url = {https://doi.org/10.1109/ISCSLP.2016.7918383}
}

Very deep convolutional neural networks for robust speech recognition

Yanmin Qian , and Philip C. Woodland

In 2016 IEEE Spoken Language Technology Workshop, SLT 2016, San Diego, CA, USA, December 13-16, 2016 , Oct 2016

Bib

@inproceedings{Qian2016e,
  author = {Qian, Yanmin and Woodland, Philip C.},
  booktitle = {2016 {IEEE} Spoken Language Technology Workshop, {SLT} 2016, San Diego, CA, USA, December 13-16, 2016},
  title = {Very deep convolutional neural networks for robust speech recognition},
  year = {2016},
  pages = {481--488},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/slt/QianW16.bib},
  doi = {10.1109/SLT.2016.7846307},
  timestamp = {Wed, 16 Oct 2019 14:14:53 +0200},
  url = {https://doi.org/10.1109/SLT.2016.7846307}
}

Evolvable dialogue state tracking for statistical dialogue management

Kai Yu, Lu Chen, Kai Sun , Qizhe Xie , and Su Zhu

Frontiers Comput. Sci., Oct 2016

Bib

@article{Yu2016,
  author = {Yu, Kai and Chen, Lu and Sun, Kai and Xie, Qizhe and Zhu, Su},
  journal = {Frontiers Comput. Sci.},
  title = {Evolvable dialogue state tracking for statistical dialogue management},
  year = {2016},
  number = {2},
  pages = {201--215},
  volume = {10},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/fcsc/YuCSXZ16.bib},
  doi = {10.1007/S11704-015-5209-4},
  timestamp = {Thu, 24 Sep 2020 01:00:00 +0200},
  url = {https://doi.org/10.1007/s11704-015-5209-4}
}

Discriminatively trained joint speaker and environment representations for adaptation of deep neural network acoustic models

Maofan Yin , Sunil Sivadas , Kai Yu, and Bin Ma

In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, March 20-25, 2016 , Oct 2016

Bib

@inproceedings{Yin2016,
  author = {Yin, Maofan and Sivadas, Sunil and Yu, Kai and Ma, Bin},
  booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
  title = {Discriminatively trained joint speaker and environment representations for adaptation of deep neural network acoustic models},
  year = {2016},
  pages = {5065--5069},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/YinSYM16.bib},
  doi = {10.1109/ICASSP.2016.7472642},
  timestamp = {Wed, 15 Mar 2023 00:00:00 +0100},
  url = {https://doi.org/10.1109/ICASSP.2016.7472642}
}

A comparative study of robustness of deep learning approaches for VAD

Sibo Tong , Hao Gu , and Kai Yu

In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, March 20-25, 2016 , Oct 2016

Bib

@inproceedings{Tong2016,
  author = {Tong, Sibo and Gu, Hao and Yu, Kai},
  booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
  title = {A comparative study of robustness of deep learning approaches for {VAD}},
  year = {2016},
  pages = {5695--5699},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/TongGY16.bib},
  doi = {10.1109/ICASSP.2016.7472768},
  timestamp = {Wed, 18 Oct 2017 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2016.7472768}
}

Phone Synchronous Decoding with CTC Lattice

Zhehuai Chen , Wei Deng , Tao Xu , and Kai Yu

In Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016 , Oct 2016

Bib

@inproceedings{Chen2016,
  author = {Chen, Zhehuai and Deng, Wei and Xu, Tao and Yu, Kai},
  booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016},
  title = {Phone Synchronous Decoding with {CTC} Lattice},
  year = {2016},
  editor = {Morgan, Nelson},
  pages = {1923--1927},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ChenDXY16.bib},
  doi = {10.21437/INTERSPEECH.2016-831},
  timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2016-831}
}

Hybrid Dialogue State Tracking for Real World Human-to-Human Dialogues

Kai Sun , Su Zhu , Lu Chen, Siqiu Yao , Xueyang Wu , and Kai Yu

In Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016 , Oct 2016

Bib

@inproceedings{Sun2016,
  author = {Sun, Kai and Zhu, Su and Chen, Lu and Yao, Siqiu and Wu, Xueyang and Yu, Kai},
  booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016},
  title = {Hybrid Dialogue State Tracking for Real World Human-to-Human Dialogues},
  year = {2016},
  editor = {Morgan, Nelson},
  pages = {2060--2064},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/SunZCYWY16.bib},
  doi = {10.21437/INTERSPEECH.2016-949},
  timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
  url = {https://doi.org/10.21437/Interspeech.2016-949}
}

On training bi-directional neural network language model with noise contrastive estimation

Tianxing He , Yu Zhang , Jasha Droppo , and Kai Yu

In 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016, Tianjin, China, October 17-20, 2016 , Oct 2016

Bib

@inproceedings{He2016,
  author = {He, Tianxing and Zhang, Yu and Droppo, Jasha and Yu, Kai},
  booktitle = {10th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2016, Tianjin, China, October 17-20, 2016},
  title = {On training bi-directional neural network language model with noise contrastive estimation},
  year = {2016},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/HeZDY16.bib},
  doi = {10.1109/ISCSLP.2016.7918423},
  timestamp = {Mon, 18 Jul 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ISCSLP.2016.7918423}
}

Rich punctuations prediction using large-scale deep learning

Xueyang Wu , Su Zhu , Yue Wu , and Kai Yu

In 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016, Tianjin, China, October 17-20, 2016 , Oct 2016

Bib

@inproceedings{Wu2016,
  author = {Wu, Xueyang and Zhu, Su and Wu, Yue and Yu, Kai},
  booktitle = {10th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2016, Tianjin, China, October 17-20, 2016},
  title = {Rich punctuations prediction using large-scale deep learning},
  year = {2016},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/WuZWY16.bib},
  doi = {10.1109/ISCSLP.2016.7918418},
  timestamp = {Wed, 15 Jan 2020 00:00:00 +0100},
  url = {https://doi.org/10.1109/ISCSLP.2016.7918418}
}

Directed automatic speech transcription error correction using bidirectional LSTM

Da Zheng , Zhehuai Chen , Yue Wu , and Kai Yu

In 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016, Tianjin, China, October 17-20, 2016 , Oct 2016

Bib

@inproceedings{Zheng2016,
  author = {Zheng, Da and Chen, Zhehuai and Wu, Yue and Yu, Kai},
  booktitle = {10th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2016, Tianjin, China, October 17-20, 2016},
  title = {Directed automatic speech transcription error correction using bidirectional {LSTM}},
  year = {2016},
  pages = {1--5},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/ZhengCWY16.bib},
  doi = {10.1109/ISCSLP.2016.7918446},
  timestamp = {Wed, 18 Oct 2017 01:00:00 +0200},
  url = {https://doi.org/10.1109/ISCSLP.2016.7918446}
}

The splab at the NTCIR-12 Short Text Conversation Task

Ke Wu , Xuan Liu , and Kai Yu

In Proceedings of the 12th NTCIR Conference on Evaluation of Information Access Technologies, National Center of Sciences, Tokyo, Japan, June 7-10, 2016 , Oct 2016

Bib

@inproceedings{Wu2016a,
  author = {Wu, Ke and Liu, Xuan and Yu, Kai},
  booktitle = {Proceedings of the 12th {NTCIR} Conference on Evaluation of Information Access Technologies, National Center of Sciences, Tokyo, Japan, June 7-10, 2016},
  title = {The splab at the {NTCIR-12} Short Text Conversation Task},
  year = {2016},
  editor = {Kando, Noriko and Sakai, Tetsuya and Sanderson, Mark},
  publisher = {National Institute of Informatics {(NII)}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/ntcir/WuLY16.bib},
  timestamp = {Wed, 01 Jun 2022 17:01:01 +0200},
  url = {http://research.nii.ac.jp/ntcir/workshop/OnlineProceedings12/pdf/ntcir/STC/04-NTCIR12-STC-WuK.pdf}
}

2015

Deep feature for text-dependent speaker verification

Yuan Liu , Yanmin Qian , Nanxin Chen , Tianfan Fu , Ya Zhang , and Kai Yu

Speech Commun., Oct 2015

Bib

@article{Liu2015,
  author = {Liu, Yuan and Qian, Yanmin and Chen, Nanxin and Fu, Tianfan and Zhang, Ya and Yu, Kai},
  journal = {Speech Commun.},
  title = {Deep feature for text-dependent speaker verification},
  year = {2015},
  pages = {1--13},
  volume = {73},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/speech/LiuQCFZY15.bib},
  doi = {10.1016/J.SPECOM.2015.07.003},
  timestamp = {Fri, 28 Apr 2023 01:00:00 +0200},
  url = {https://doi.org/10.1016/j.specom.2015.07.003}
}

Multi-task joint-learning of deep neural networks for robust speech recognition

Yanmin Qian , Maofan Yin , Yongbin You , and Kai Yu

In 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015, Scottsdale, AZ, USA, December 13-17, 2015 , Oct 2015

Bib

@inproceedings{Qian2015,
  author = {Qian, Yanmin and Yin, Maofan and You, Yongbin and Yu, Kai},
  booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding, {ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015},
  title = {Multi-task joint-learning of deep neural networks for robust speech recognition},
  year = {2015},
  pages = {310--316},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/asru/QianYYY15.bib},
  doi = {10.1109/ASRU.2015.7404810},
  timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
  url = {https://doi.org/10.1109/ASRU.2015.7404810}
}

Cambridge university transcription systems for the multi-genre broadcast challenge

Philip C. Woodland , Xunying Liu , Yanmin Qian , Chao Zhang , Mark J. F. Gales , Penny Karanasou , Pierre Lanchantin , and Linlin Wang

In 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015, Scottsdale, AZ, USA, December 13-17, 2015 , Oct 2015

Bib

@inproceedings{Woodland2015,
  author = {Woodland, Philip C. and Liu, Xunying and Qian, Yanmin and Zhang, Chao and Gales, Mark J. F. and Karanasou, Penny and Lanchantin, Pierre and Wang, Linlin},
  booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding, {ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015},
  title = {Cambridge university transcription systems for the multi-genre broadcast challenge},
  year = {2015},
  pages = {639--646},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/asru/WoodlandLQZGKLW15.bib},
  doi = {10.1109/ASRU.2015.7404856},
  timestamp = {Tue, 23 Jun 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/ASRU.2015.7404856}
}

The development of the cambridge university alignment systems for the multi-genre broadcast challenge

Pierre Lanchantin , Mark J. F. Gales , Penny Karanasou , Xunying Liu , Yanmin Qian , Linlin Wang , Philip C. Woodland , and Chao Zhang

In 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015, Scottsdale, AZ, USA, December 13-17, 2015 , Oct 2015

Bib

@inproceedings{Lanchantin2015,
  author = {Lanchantin, Pierre and Gales, Mark J. F. and Karanasou, Penny and Liu, Xunying and Qian, Yanmin and Wang, Linlin and Woodland, Philip C. and Zhang, Chao},
  booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding, {ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015},
  title = {The development of the cambridge university alignment systems for the multi-genre broadcast challenge},
  year = {2015},
  pages = {647--653},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/asru/LanchantinGKLQW15.bib},
  doi = {10.1109/ASRU.2015.7404857},
  timestamp = {Tue, 23 Jun 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/ASRU.2015.7404857}
}

Speaker diarisation and longitudinal linking in multi-genre broadcast data

Penny Karanasou , Mark J. F. Gales , Pierre Lanchantin , Xunying Liu , Yanmin Qian , Linlin Wang , Philip C. Woodland , and Chao Zhang

In 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015, Scottsdale, AZ, USA, December 13-17, 2015 , Oct 2015

Bib

@inproceedings{Karanasou2015,
  author = {Karanasou, Penny and Gales, Mark J. F. and Lanchantin, Pierre and Liu, Xunying and Qian, Yanmin and Wang, Linlin and Woodland, Philip C. and Zhang, Chao},
  booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding, {ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015},
  title = {Speaker diarisation and longitudinal linking in multi-genre broadcast data},
  year = {2015},
  pages = {660--666},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/asru/KaranasouGLLQWW15.bib},
  doi = {10.1109/ASRU.2015.7404859},
  timestamp = {Tue, 23 Jun 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/ASRU.2015.7404859}
}

Local trajectory based speech enhancement for robust speech recognition with deep neural network

Yongbin You , Yanmin Qian , and Kai Yu

In IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015, Chengdu, China, July 12-15, 2015 , Oct 2015

Bib

@inproceedings{You2015,
  author = {You, Yongbin and Qian, Yanmin and Yu, Kai},
  booktitle = {{IEEE} China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015, Chengdu, China, July 12-15, 2015},
  title = {Local trajectory based speech enhancement for robust speech recognition with deep neural network},
  year = {2015},
  pages = {5--9},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/chinasip/YouQY15.bib},
  doi = {10.1109/CHINASIP.2015.7230351},
  timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
  url = {https://doi.org/10.1109/ChinaSIP.2015.7230351}
}

An investigation on DNN-derived bottleneck features for GMM-HMM based robust speech recognition

Yongbin You , Yanmin Qian , Tianxing He , and Kai Yu

In IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015, Chengdu, China, July 12-15, 2015 , Oct 2015

Bib

@inproceedings{You2015a,
  author = {You, Yongbin and Qian, Yanmin and He, Tianxing and Yu, Kai},
  booktitle = {{IEEE} China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015, Chengdu, China, July 12-15, 2015},
  title = {An investigation on DNN-derived bottleneck features for {GMM-HMM} based robust speech recognition},
  year = {2015},
  pages = {30--34},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/chinasip/YouQHY15.bib},
  doi = {10.1109/CHINASIP.2015.7230356},
  timestamp = {Tue, 17 Oct 2017 01:00:00 +0200},
  url = {https://doi.org/10.1109/ChinaSIP.2015.7230356}
}

Cluster adaptive training for deep neural network

Tian Tan , Yanmin Qian , Maofan Yin , Yimeng Zhuang , and Kai Yu

In 2015 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2015, South Brisbane, Queensland, Australia, April 19-24, 2015 , Oct 2015

Bib

@inproceedings{Tan2015,
  author = {Tan, Tian and Qian, Yanmin and Yin, Maofan and Zhuang, Yimeng and Yu, Kai},
  booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia, April 19-24, 2015},
  title = {Cluster adaptive training for deep neural network},
  year = {2015},
  pages = {4325--4329},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/TanQYZY15.bib},
  doi = {10.1109/ICASSP.2015.7178787},
  timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
  url = {https://doi.org/10.1109/ICASSP.2015.7178787}
}

A novel static parameter calculation method for model compensation

Suliang Bu , Yunxin Zhao , Yanmin Qian , and Kai Yu

In 2015 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2015, South Brisbane, Queensland, Australia, April 19-24, 2015 , Oct 2015

Bib

@inproceedings{Bu2015,
  author = {Bu, Suliang and Zhao, Yunxin and Qian, Yanmin and Yu, Kai},
  booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia, April 19-24, 2015},
  title = {A novel static parameter calculation method for model compensation},
  year = {2015},
  pages = {4510--4514},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/BuZQY15.bib},
  doi = {10.1109/ICASSP.2015.7178824},
  timestamp = {Tue, 17 Oct 2017 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2015.7178824}
}

Recurrent neural network language model with structured word embeddings for speech recognition

Tianxing He , Xu Xiang , Yanmin Qian , and Kai Yu

In 2015 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2015, South Brisbane, Queensland, Australia, April 19-24, 2015 , Oct 2015

Bib

@inproceedings{He2015,
  author = {He, Tianxing and Xiang, Xu and Qian, Yanmin and Yu, Kai},
  booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia, April 19-24, 2015},
  title = {Recurrent neural network language model with structured word embeddings for speech recognition},
  year = {2015},
  pages = {5396--5400},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/HeXQY15.bib},
  doi = {10.1109/ICASSP.2015.7179002},
  timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2015.7179002}
}

Automatic model redundancy reduction for fast back-propagation for deep neural networks in speech recognition

Yanmin Qian , Tianxing He , Wei Deng , and Kai Yu

In 2015 International Joint Conference on Neural Networks, IJCNN 2015, Killarney, Ireland, July 12-17, 2015 , Oct 2015

Bib

@inproceedings{Qian2015a,
  author = {Qian, Yanmin and He, Tianxing and Deng, Wei and Yu, Kai},
  booktitle = {2015 International Joint Conference on Neural Networks, {IJCNN} 2015, Killarney, Ireland, July 12-17, 2015},
  title = {Automatic model redundancy reduction for fast back-propagation for deep neural networks in speech recognition},
  year = {2015},
  pages = {1--6},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/ijcnn/QianHDY15.bib},
  doi = {10.1109/IJCNN.2015.7280335},
  timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
  url = {https://doi.org/10.1109/IJCNN.2015.7280335}
}

Multi-task learning for text-dependent speaker verification

Nanxin Chen , Yanmin Qian , and Kai Yu

In INTERSPEECH 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015 , Oct 2015

Bib

@inproceedings{Chen2015,
  author = {Chen, Nanxin and Qian, Yanmin and Yu, Kai},
  booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015},
  title = {Multi-task learning for text-dependent speaker verification},
  year = {2015},
  pages = {185--189},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ChenQY15.bib},
  doi = {10.21437/INTERSPEECH.2015-81},
  timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2015-81}
}

Robust deep feature for spoofing detection - the SJTU system for ASVspoof 2015 challenge

Nanxin Chen , Yanmin Qian , Heinrich Dinkel , Bo Chen , and Kai Yu

In INTERSPEECH 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015 , Oct 2015

Bib

@inproceedings{Chen2015a,
  author = {Chen, Nanxin and Qian, Yanmin and Dinkel, Heinrich and Chen, Bo and Yu, Kai},
  booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015},
  title = {Robust deep feature for spoofing detection - the {SJTU} system for ASVspoof 2015 challenge},
  year = {2015},
  pages = {2097--2101},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ChenQDCY15.bib},
  doi = {10.21437/INTERSPEECH.2015-474},
  timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2015-474}
}

Very deep convolutional neural networks for LVCSR

Mengxiao Bi , Yanmin Qian , and Kai Yu

In INTERSPEECH 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015 , Oct 2015

Bib

@inproceedings{Bi2015,
  author = {Bi, Mengxiao and Qian, Yanmin and Yu, Kai},
  booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015},
  title = {Very deep convolutional neural networks for {LVCSR}},
  year = {2015},
  pages = {3259--3263},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/BiQY15.bib},
  doi = {10.21437/INTERSPEECH.2015-656},
  timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2015-656}
}

Paragraph vector based topic model for language model adaptation

Wengong Jin , Tianxing He , Yanmin Qian , and Kai Yu

In INTERSPEECH 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015 , Oct 2015

Bib

@inproceedings{Jin2015,
  author = {Jin, Wengong and He, Tianxing and Qian, Yanmin and Yu, Kai},
  booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015},
  title = {Paragraph vector based topic model for language model adaptation},
  year = {2015},
  pages = {3516--3520},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/JinHQY15.bib},
  doi = {10.21437/INTERSPEECH.2015-697},
  timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2015-697}
}

Constrained Markov Bayesian Polynomial for Efficient Dialogue State Tracking

Kai Yu, Kai Sun , Lu Chen , and Su Zhu

IEEE ACM Trans. Audio Speech Lang. Process., Oct 2015

Bib

@article{Yu2015,
  author = {Yu, Kai and Sun, Kai and Chen, Lu and Zhu, Su},
  journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
  title = {Constrained Markov Bayesian Polynomial for Efficient Dialogue State Tracking},
  year = {2015},
  number = {12},
  pages = {2177--2188},
  volume = {23},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/taslp/YuSCZ15.bib},
  doi = {10.1109/TASLP.2015.2470597},
  timestamp = {Thu, 24 Sep 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/TASLP.2015.2470597}
}

An investigation of context clustering for statistical speech synthesis with deep neural network

Bo Chen , Zhehuai Chen , Jiachen Xu , and Kai Yu

In INTERSPEECH 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015 , Oct 2015

Bib

@inproceedings{Chen2015b,
  author = {Chen, Bo and Chen, Zhehuai and Xu, Jiachen and Yu, Kai},
  booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015},
  title = {An investigation of context clustering for statistical speech synthesis with deep neural network},
  year = {2015},
  pages = {2212--2216},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/ChenCXY15.bib},
  doi = {10.21437/INTERSPEECH.2015-127},
  timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2015-127}
}

Recurrent Polynomial Network for Dialogue State Tracking with Mismatched Semantic Parsers

Qizhe Xie , Kai Sun , Su Zhu , Lu Chen, and Kai Yu

In Proceedings of the SIGDIAL 2015 Conference, The 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2-4 September 2015, Prague, Czech Republic , Oct 2015

Bib

@inproceedings{Xie2015,
  author = {Xie, Qizhe and Sun, Kai and Zhu, Su and Chen, Lu and Yu, Kai},
  booktitle = {Proceedings of the {SIGDIAL} 2015 Conference, The 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2-4 September 2015, Prague, Czech Republic},
  title = {Recurrent Polynomial Network for Dialogue State Tracking with Mismatched Semantic Parsers},
  year = {2015},
  pages = {295--304},
  publisher = {The Association for Computer Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/sigdial/XieSZCY15.bib},
  doi = {10.18653/V1/W15-4641},
  timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/w15-4641}
}

Hyper-parameter Optimisation of Gaussian Process Reinforcement Learning for Statistical Dialogue Management

Lu Chen, Pei-Hao Su , and Milica Gasic

In Proceedings of the SIGDIAL 2015 Conference, The 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2-4 September 2015, Prague, Czech Republic , Oct 2015

Bib

@inproceedings{Chen2015c,
  author = {Chen, Lu and Su, Pei{-}Hao and Gasic, Milica},
  booktitle = {Proceedings of the {SIGDIAL} 2015 Conference, The 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2-4 September 2015, Prague, Czech Republic},
  title = {Hyper-parameter Optimisation of Gaussian Process Reinforcement Learning for Statistical Dialogue Management},
  year = {2015},
  pages = {407--411},
  publisher = {The Association for Computer Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/sigdial/ChenSG15.bib},
  doi = {10.18653/V1/W15-4653},
  timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
  url = {https://doi.org/10.18653/v1/w15-4653}
}

2014

Stochastic data sweeping for fast DNN training

Wei Deng , Yanmin Qian , Yuchen Fan , Tianfan Fu , and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2014, Florence, Italy, May 4-9, 2014 , Oct 2014

Bib

@inproceedings{Deng2014,
  author = {Deng, Wei and Qian, Yanmin and Fan, Yuchen and Fu, Tianfan and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2014, Florence, Italy, May 4-9, 2014},
  title = {Stochastic data sweeping for fast {DNN} training},
  year = {2014},
  pages = {240--244},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/DengQFFY14.bib},
  doi = {10.1109/ICASSP.2014.6853594},
  timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
  url = {https://doi.org/10.1109/ICASSP.2014.6853594}
}

Reshaping deep neural network for fast decoding by node-pruning

Tianxing He , Yuchen Fan , Yanmin Qian , Tian Tan , and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2014, Florence, Italy, May 4-9, 2014 , Oct 2014

Bib

@inproceedings{He2014,
  author = {He, Tianxing and Fan, Yuchen and Qian, Yanmin and Tan, Tian and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2014, Florence, Italy, May 4-9, 2014},
  title = {Reshaping deep neural network for fast decoding by node-pruning},
  year = {2014},
  pages = {245--249},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/HeFQTY14.bib},
  doi = {10.1109/ICASSP.2014.6853595},
  timestamp = {Sat, 31 Mar 2018 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2014.6853595}
}

Second order vector taylor series based robust speech recognition

Suliang Bu , Yanmin Qian , Khe Chai Sim , Yongbin You , and Kai Yu

In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2014, Florence, Italy, May 4-9, 2014 , Oct 2014

Bib

@inproceedings{Bu2014,
  author = {Bu, Suliang and Qian, Yanmin and Sim, Khe Chai and You, Yongbin and Yu, Kai},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2014, Florence, Italy, May 4-9, 2014},
  title = {Second order vector taylor series based robust speech recognition},
  year = {2014},
  pages = {1769--1773},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icassp/BuQSYY14.bib},
  doi = {10.1109/ICASSP.2014.6853902},
  timestamp = {Tue, 17 Oct 2017 01:00:00 +0200},
  url = {https://doi.org/10.1109/ICASSP.2014.6853902}
}

Speaker verification with deep features

Yuan Liu , Tianfan Fu , Yuchen Fan , Yanmin Qian , and Kai Yu

In 2014 International Joint Conference on Neural Networks, IJCNN 2014, Beijing, China, July 6-11, 2014 , Oct 2014

Bib

@inproceedings{Liu2014,
  author = {Liu, Yuan and Fu, Tianfan and Fan, Yuchen and Qian, Yanmin and Yu, Kai},
  booktitle = {2014 International Joint Conference on Neural Networks, {IJCNN} 2014, Beijing, China, July 6-11, 2014},
  title = {Speaker verification with deep features},
  year = {2014},
  pages = {747--753},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/ijcnn/LiuFFQY14.bib},
  doi = {10.1109/IJCNN.2014.6889708},
  timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
  url = {https://doi.org/10.1109/IJCNN.2014.6889708}
}

Tandem deep features for text-dependent speaker verification

Tianfan Fu , Yanmin Qian , Yuan Liu , and Kai Yu

In INTERSPEECH 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014 , Oct 2014

Bib

@inproceedings{Fu2014,
  author = {Fu, Tianfan and Qian, Yanmin and Liu, Yuan and Yu, Kai},
  booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014},
  title = {Tandem deep features for text-dependent speaker verification},
  year = {2014},
  editor = {Li, Haizhou and Meng, Helen M. and Ma, Bin and Chng, Engsiong and Xie, Lei},
  pages = {1327--1331},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/FuQLY14.bib},
  doi = {10.21437/INTERSPEECH.2014-329},
  timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2014-329}
}

A novel dynamic parameters calculation approach for model compensation

Suliang Bu , Yanmin Qian , and Kai Yu

In INTERSPEECH 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014 , Oct 2014

Bib

@inproceedings{Bu2014a,
  author = {Bu, Suliang and Qian, Yanmin and Yu, Kai},
  booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014},
  title = {A novel dynamic parameters calculation approach for model compensation},
  year = {2014},
  editor = {Li, Haizhou and Meng, Helen M. and Ma, Bin and Chng, Engsiong and Xie, Lei},
  pages = {2744--2748},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/BuQY14.bib},
  doi = {10.21437/INTERSPEECH.2014-159},
  timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2014-159}
}

Acoustic emotion recognition using deep neural network

Jianwei Niu , Yanmin Qian , and Kai Yu

In The 9th International Symposium on Chinese Spoken Language Processing, Singapore, September 12-14, 2014 , Oct 2014

Bib

@inproceedings{Niu2014,
  author = {Niu, Jianwei and Qian, Yanmin and Yu, Kai},
  booktitle = {The 9th International Symposium on Chinese Spoken Language Processing, Singapore, September 12-14, 2014},
  title = {Acoustic emotion recognition using deep neural network},
  year = {2014},
  editor = {Dong, Minghui and Tao, Jianhua and Li, Haizhou and Zheng, Thomas Fang and Lu, Yanfeng},
  pages = {128--132},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/iscslp/NiuQY14.bib},
  doi = {10.1109/ISCSLP.2014.6936657},
  timestamp = {Mon, 18 Mar 2024 17:29:23 +0100},
  url = {https://doi.org/10.1109/ISCSLP.2014.6936657}
}

The SJTU System for Dialog State Tracking Challenge 2

Kai Sun , Lu Chen , Su Zhu , and Kai Yu

In Proceedings of the SIGDIAL 2014 Conference, The 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 18-20 June 2014, Philadelphia, PA, USA , Oct 2014

Bib

@inproceedings{Sun2014,
  author = {Sun, Kai and Chen, Lu and Zhu, Su and Yu, Kai},
  booktitle = {Proceedings of the {SIGDIAL} 2014 Conference, The 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 18-20 June 2014, Philadelphia, PA, {USA}},
  title = {The {SJTU} System for Dialog State Tracking Challenge 2},
  year = {2014},
  pages = {318--326},
  publisher = {The Association for Computer Linguistics},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/sigdial/SunCZY14.bib},
  doi = {10.3115/V1/W14-4343},
  timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
  url = {https://doi.org/10.3115/v1/w14-4343}
}

A generalized rule based tracker for dialogue state tracking

Kai Sun , Lu Chen , Su Zhu , and Kai Yu

In 2014 IEEE Spoken Language Technology Workshop, SLT 2014, South Lake Tahoe, NV, USA, December 7-10, 2014 , Oct 2014

Bib

@inproceedings{Sun2014a,
  author = {Sun, Kai and Chen, Lu and Zhu, Su and Yu, Kai},
  booktitle = {2014 {IEEE} Spoken Language Technology Workshop, {SLT} 2014, South Lake Tahoe, NV, USA, December 7-10, 2014},
  title = {A generalized rule based tracker for dialogue state tracking},
  year = {2014},
  pages = {330--335},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/slt/SunCZY14.bib},
  doi = {10.1109/SLT.2014.7078596},
  timestamp = {Thu, 24 Sep 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/SLT.2014.7078596}
}

Semantic parser enhancement for dialogue domain extension with little data

Su Zhu , Lu Chen, Kai Sun , Da Zheng , and Kai Yu

In 2014 IEEE Spoken Language Technology Workshop, SLT 2014, South Lake Tahoe, NV, USA, December 7-10, 2014 , Oct 2014

Bib

@inproceedings{Zhu2014,
  author = {Zhu, Su and Chen, Lu and Sun, Kai and Zheng, Da and Yu, Kai},
  booktitle = {2014 {IEEE} Spoken Language Technology Workshop, {SLT} 2014, South Lake Tahoe, NV, USA, December 7-10, 2014},
  title = {Semantic parser enhancement for dialogue domain extension with little data},
  year = {2014},
  pages = {336--341},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/slt/ZhuCSZY14.bib},
  doi = {10.1109/SLT.2014.7078597},
  timestamp = {Thu, 24 Sep 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/SLT.2014.7078597}
}

2013

Combination of data borrowing strategies for low-resource LVCSR

Yanmin Qian , Kai Yu, and Jia Liu

In 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic, December 8-12, 2013 , Oct 2013

Bib

@inproceedings{Qian2013,
  author = {Qian, Yanmin and Yu, Kai and Liu, Jia},
  booktitle = {2013 {IEEE} Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic, December 8-12, 2013},
  title = {Combination of data borrowing strategies for low-resource {LVCSR}},
  year = {2013},
  pages = {404--409},
  publisher = {{IEEE}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/asru/QianYL13.bib},
  doi = {10.1109/ASRU.2013.6707764},
  timestamp = {Mon, 20 Apr 2020 01:00:00 +0200},
  url = {https://doi.org/10.1109/ASRU.2013.6707764}
}

MLP-HMM two-stage unsupervised training for low-resource languages on conversational telephone speech recognition

Yanmin Qian , and Jia Liu

In INTERSPEECH 2013, 14th Annual Conference of the International Speech Communication Association, Lyon, France, August 25-29, 2013 , Oct 2013

Bib

@inproceedings{Qian2013a,
  author = {Qian, Yanmin and Liu, Jia},
  booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech Communication Association, Lyon, France, August 25-29, 2013},
  title = {{MLP-HMM} two-stage unsupervised training for low-resource languages on conversational telephone speech recognition},
  year = {2013},
  editor = {Bimbot, Fr{\'{e}}d{\'{e}}ric and Cerisara, Christophe and Fougeron, C{\'{e}}cile and Gravier, Guillaume and Lamel, Lori and Pellegrino, Fran{\c{c}}ois and Perrier, Pascal},
  pages = {1816--1820},
  publisher = {{ISCA}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/interspeech/QianL13.bib},
  doi = {10.21437/INTERSPEECH.2013-448},
  timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
  url = {https://doi.org/10.21437/Interspeech.2013-448}
}

A New Word Language Model Evaluation Metric for Character Based Languages

Peilu Wang , Ruihua Sun , Hai Zhao , and Kai Yu

In Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data - 12th China National Conference, CCL 2013 and First International Symposium, NLP-NABD 2013, Suzhou, China, October 10-12, 2013. Proceedings , Oct 2013

Bib

@inproceedings{Wang2013,
  author = {Wang, Peilu and Sun, Ruihua and Zhao, Hai and Yu, Kai},
  booktitle = {Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data - 12th China National Conference, {CCL} 2013 and First International Symposium, {NLP-NABD} 2013, Suzhou, China, October 10-12, 2013. Proceedings},
  title = {A New Word Language Model Evaluation Metric for Character Based Languages},
  year = {2013},
  editor = {Sun, Maosong and Zhang, Min and Lin, Dekang and Wang, Haifeng},
  pages = {315--324},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  volume = {8202},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/cncl/WangSZY13.bib},
  doi = {10.1007/978-3-642-41491-6\_29},
  timestamp = {Fri, 01 Sep 2023 13:50:17 +0200},
  url = {https://doi.org/10.1007/978-3-642-41491-6\_29}
}

2012

Introduction to the Issue on Advances in Spoken Dialogue Systems and Mobile Interface

Jason D. Williams , Kai Yu, Brahim Chaib-draa , Oliver Lemon , Roberto Pieraccini , Olivier Pietquin , Pascal Poupart , and Steve J. Young

IEEE J. Sel. Top. Signal Process., Oct 2012

Bib

@article{Williams2012,
  author = {Williams, Jason D. and Yu, Kai and Chaib{-}draa, Brahim and Lemon, Oliver and Pieraccini, Roberto and Pietquin, Olivier and Poupart, Pascal and Young, Steve J.},
  journal = {{IEEE} J. Sel. Top. Signal Process.},
  title = {Introduction to the Issue on Advances in Spoken Dialogue Systems and Mobile Interface},
  year = {2012},
  number = {8},
  pages = {889--890},
  volume = {6},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/journals/jstsp/WilliamsYCLPPPY12.bib},
  doi = {10.1109/JSTSP.2012.2234401},
  timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
  url = {https://doi.org/10.1109/JSTSP.2012.2234401}
}

ICMI’12 grand challenge: haptic voice recognition

Khe Chai Sim , Shengdong Zhao , Kai Yu, and Hank Liao

In International Conference on Multimodal Interaction, ICMI ’12, Santa Monica, CA, USA, October 22-26, 2012 , Oct 2012

Bib

@inproceedings{Sim2012,
  author = {Sim, Khe Chai and Zhao, Shengdong and Yu, Kai and Liao, Hank},
  booktitle = {International Conference on Multimodal Interaction, {ICMI} '12, Santa Monica, CA, USA, October 22-26, 2012},
  title = {ICMI'12 grand challenge: haptic voice recognition},
  year = {2012},
  editor = {Morency, Louis{-}Philippe and Bohus, Dan and Aghajan, Hamid K. and Cassell, Justine and Nijholt, Anton and Epps, Julien},
  pages = {363--370},
  publisher = {{ACM}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icmi/SimZYL12.bib},
  doi = {10.1145/2388676.2388759},
  timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
  url = {https://doi.org/10.1145/2388676.2388759}
}

Development of the 2012 SJTU HVR system

Hainan Xu , Yuchen Fan , and Kai Yu

In International Conference on Multimodal Interaction, ICMI ’12, Santa Monica, CA, USA, October 22-26, 2012 , Oct 2012

Bib

@inproceedings{Xu2012,
  author = {Xu, Hainan and Fan, Yuchen and Yu, Kai},
  booktitle = {International Conference on Multimodal Interaction, {ICMI} '12, Santa Monica, CA, USA, October 22-26, 2012},
  title = {Development of the 2012 {SJTU} {HVR} system},
  year = {2012},
  editor = {Morency, Louis{-}Philippe and Bohus, Dan and Aghajan, Hamid K. and Cassell, Justine and Nijholt, Anton and Epps, Julien},
  pages = {539--544},
  publisher = {{ACM}},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl = {https://dblp.org/rec/conf/icmi/XuFY12.bib},
  doi = {10.1145/2388676.2388790},
  timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
  url = {https://doi.org/10.1145/2388676.2388790}
}