Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Yanmin Qian

Yanmin Qian

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


Nov 17, 2021
Wangyou Zhang, Zhuo Chen, Naoyuki Kanda, Shujie Liu, Jinyu Li, Sefik Emre Eskimez, Takuya Yoshioka, Xiong Xiao, Zhong Meng, Yanmin Qian, Furu Wei

Figure 1 for Separating Long-Form Speech with Group-Wise Permutation Invariant Training
Figure 2 for Separating Long-Form Speech with Group-Wise Permutation Invariant Training
Figure 3 for Separating Long-Form Speech with Group-Wise Permutation Invariant Training
Figure 4 for Separating Long-Form Speech with Group-Wise Permutation Invariant Training
* 5 pages, 3 figures, 3 tables, submitted to IEEE ICASSP 2022 
  Access Paper or Ask Questions

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


Oct 29, 2021
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, Furu Wei

Figure 1 for WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
Figure 2 for WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
Figure 3 for WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
Figure 4 for WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing

  Access Paper or Ask Questions

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


Oct 27, 2021
Wangyou Zhang, Jing Shi, Chenda Li, Shinji Watanabe, Yanmin Qian

Figure 1 for Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions
Figure 2 for Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions
Figure 3 for Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions
* 5 pages, 3 figures, accepted by IEEE WASPAA 2021 
  Access Paper or Ask Questions

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


Oct 23, 2021
Wei Wang, Shuo Ren, Yao Qian, Shujie Liu, Yu Shi, Yanmin Qian, Michael Zeng

Figure 1 for Optimizing Alignment of Speech and Language Latent Spaces for End-to-End Speech Recognition and Understanding
Figure 2 for Optimizing Alignment of Speech and Language Latent Spaces for End-to-End Speech Recognition and Understanding
Figure 3 for Optimizing Alignment of Speech and Language Latent Spaces for End-to-End Speech Recognition and Understanding
Figure 4 for Optimizing Alignment of Speech and Language Latent Spaces for End-to-End Speech Recognition and Understanding
* submitted to ICASSP 2022 
  Access Paper or Ask Questions

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


Oct 12, 2021
Zhengyang Chen, Sanyuan Chen, Yu Wu, Yao Qian, Chengyi Wang, Shujie Liu, Yanmin Qian, Michael Zeng

Figure 1 for Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification
Figure 2 for Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification
Figure 3 for Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification
Figure 4 for Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification
* submitted to ICASSP 2022 
  Access Paper or Ask Questions

Self-Supervised Learning Based Domain Adaptation for Robust Speaker Verification


Aug 31, 2021
Zhengyang Chen, Shuai Wang, Yanmin Qian

Figure 1 for Self-Supervised Learning Based Domain Adaptation for Robust Speaker Verification
Figure 2 for Self-Supervised Learning Based Domain Adaptation for Robust Speaker Verification
Figure 3 for Self-Supervised Learning Based Domain Adaptation for Robust Speaker Verification
Figure 4 for Self-Supervised Learning Based Domain Adaptation for Robust Speaker Verification
* Published in: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 
  Access Paper or Ask Questions

Basis-MelGAN: Efficient Neural Vocoder Based on Audio Decomposition


Jun 25, 2021
Zhengxi Liu, Yanmin Qian

Figure 1 for Basis-MelGAN: Efficient Neural Vocoder Based on Audio Decomposition
Figure 2 for Basis-MelGAN: Efficient Neural Vocoder Based on Audio Decomposition
Figure 3 for Basis-MelGAN: Efficient Neural Vocoder Based on Audio Decomposition
Figure 4 for Basis-MelGAN: Efficient Neural Vocoder Based on Audio Decomposition
* Accepted to INTERSPEECH 2021 
  Access Paper or Ask Questions

Dual-Path Modeling for Long Recording Speech Separation in Meetings


Feb 23, 2021
Chenda Li, Zhuo Chen, Yi Luo, Cong Han, Tianyan Zhou, Keisuke Kinoshita, Marc Delcroix, Shinji Watanabe, Yanmin Qian

Figure 1 for Dual-Path Modeling for Long Recording Speech Separation in Meetings
Figure 2 for Dual-Path Modeling for Long Recording Speech Separation in Meetings
Figure 3 for Dual-Path Modeling for Long Recording Speech Separation in Meetings
Figure 4 for Dual-Path Modeling for Long Recording Speech Separation in Meetings
* Accepted by ICASSP 2021 
  Access Paper or Ask Questions

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


Feb 23, 2021
Wangyou Zhang, Christoph Boeddeker, Shinji Watanabe, Tomohiro Nakatani, Marc Delcroix, Keisuke Kinoshita, Tsubasa Ochiai, Naoyuki Kamo, Reinhold Haeb-Umbach, Yanmin Qian

Figure 1 for End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend
Figure 2 for End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend
Figure 3 for End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend
* 5 pages, 1 figure, accepted by ICASSP 2021 
  Access Paper or Ask Questions

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


Feb 20, 2021
Xian Shi, Fan Yu, Yizhou Lu, Yuhao Liang, Qiangze Feng, Daliang Wang, Yanmin Qian, Lei Xie

Figure 1 for The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods
Figure 2 for The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods
Figure 3 for The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods
* Accepted by ICASSP 2021 
  Access Paper or Ask Questions

AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challenge


Feb 19, 2021
Houjun Huang, Xu Xiang, Yexin Yang, Rao Ma, Yanmin Qian

Figure 1 for AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challenge
Figure 2 for AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challenge
Figure 3 for AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challenge
Figure 4 for AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challenge
* Accepted to ICASSP 2021 
  Access Paper or Ask Questions

Unit selection synthesis based data augmentation for fixed phrase speaker verification


Feb 19, 2021
Houjun Huang, Xu Xiang, Fei Zhao, Shuai Wang, Yanmin Qian

Figure 1 for Unit selection synthesis based data augmentation for fixed phrase speaker verification
Figure 2 for Unit selection synthesis based data augmentation for fixed phrase speaker verification
Figure 3 for Unit selection synthesis based data augmentation for fixed phrase speaker verification
Figure 4 for Unit selection synthesis based data augmentation for fixed phrase speaker verification
* Accepted to ICASSP 2021 
  Access Paper or Ask Questions

Data Augmentation for End-to-end Code-switching Speech Recognition


Nov 04, 2020
Chenpeng Du, Hao Li, Yizhou Lu, Lan Wang, Yanmin Qian

Figure 1 for Data Augmentation for End-to-end Code-switching Speech Recognition
Figure 2 for Data Augmentation for End-to-end Code-switching Speech Recognition
Figure 3 for Data Augmentation for End-to-end Code-switching Speech Recognition
Figure 4 for Data Augmentation for End-to-end Code-switching Speech Recognition
* Accepted by SLT2021 
  Access Paper or Ask Questions

Future Vector Enhanced LSTM Language Model for LVCSR


Jul 31, 2020
Qi Liu, Yanmin Qian, Kai Yu

Figure 1 for Future Vector Enhanced LSTM Language Model for LVCSR
Figure 2 for Future Vector Enhanced LSTM Language Model for LVCSR
Figure 3 for Future Vector Enhanced LSTM Language Model for LVCSR
Figure 4 for Future Vector Enhanced LSTM Language Model for LVCSR
* Accepted by ASRU-2017 
  Access Paper or Ask Questions

End-to-End Multi-speaker Speech Recognition with Transformer


Feb 13, 2020
Xuankai Chang, Wangyou Zhang, Yanmin Qian, Jonathan Le Roux, Shinji Watanabe

Figure 1 for End-to-End Multi-speaker Speech Recognition with Transformer
Figure 2 for End-to-End Multi-speaker Speech Recognition with Transformer
Figure 3 for End-to-End Multi-speaker Speech Recognition with Transformer
Figure 4 for End-to-End Multi-speaker Speech Recognition with Transformer
* To appear in ICASSP 2020 
  Access Paper or Ask Questions

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


Oct 16, 2019
Xuankai Chang, Wangyou Zhang, Yanmin Qian, Jonathan Le Roux, Shinji Watanabe

Figure 1 for MIMO-SPEECH: End-to-End Multi-Channel Multi-Speaker Speech Recognition
Figure 2 for MIMO-SPEECH: End-to-End Multi-Channel Multi-Speaker Speech Recognition
Figure 3 for MIMO-SPEECH: End-to-End Multi-Channel Multi-Speaker Speech Recognition
Figure 4 for MIMO-SPEECH: End-to-End Multi-Channel Multi-Speaker Speech Recognition
* Accepted at ASRU 2019 
  Access Paper or Ask Questions

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


Jun 18, 2019
Xu Xiang, Shuai Wang, Houjun Huang, Yanmin Qian, Kai Yu

Figure 1 for Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition
Figure 2 for Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition
Figure 3 for Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition
Figure 4 for Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition
* not accepted by INTERSPEECH 2019 
  Access Paper or Ask Questions

End-to-End Monaural Multi-speaker ASR System without Pretraining


Nov 05, 2018
Xuankai Chang, Yanmin Qian, Kai Yu, Shinji Watanabe

Figure 1 for End-to-End Monaural Multi-speaker ASR System without Pretraining
Figure 2 for End-to-End Monaural Multi-speaker ASR System without Pretraining
Figure 3 for End-to-End Monaural Multi-speaker ASR System without Pretraining
Figure 4 for End-to-End Monaural Multi-speaker ASR System without Pretraining
* submitted to ICASSP2019 
  Access Paper or Ask Questions

Sequence Discriminative Training for Deep Learning based Acoustic Keyword Spotting


Aug 02, 2018
Zhehuai Chen, Yanmin Qian, Kai Yu

Figure 1 for Sequence Discriminative Training for Deep Learning based Acoustic Keyword Spotting
Figure 2 for Sequence Discriminative Training for Deep Learning based Acoustic Keyword Spotting
Figure 3 for Sequence Discriminative Training for Deep Learning based Acoustic Keyword Spotting
Figure 4 for Sequence Discriminative Training for Deep Learning based Acoustic Keyword Spotting
* Speech Communication, vol. 102, 100-111, 2018 
 * accepted by Speech Communication, 08/02/2018 
  Access Paper or Ask Questions

Single-Channel Multi-talker Speech Recognition with Permutation Invariant Training


Jul 19, 2017
Yanmin Qian, Xuankai Chang, Dong Yu

Figure 1 for Single-Channel Multi-talker Speech Recognition with Permutation Invariant Training
Figure 2 for Single-Channel Multi-talker Speech Recognition with Permutation Invariant Training
Figure 3 for Single-Channel Multi-talker Speech Recognition with Permutation Invariant Training
Figure 4 for Single-Channel Multi-talker Speech Recognition with Permutation Invariant Training
* 11 pages, 6 figures, Submitted to IEEE/ACM Transactions on Audio, Speech and Language Processing. arXiv admin note: text overlap with arXiv:1704.01985 
  Access Paper or Ask Questions

Recognizing Multi-talker Speech with Permutation Invariant Training


Jun 19, 2017
Dong Yu, Xuankai Chang, Yanmin Qian

Figure 1 for Recognizing Multi-talker Speech with Permutation Invariant Training
Figure 2 for Recognizing Multi-talker Speech with Permutation Invariant Training
Figure 3 for Recognizing Multi-talker Speech with Permutation Invariant Training
Figure 4 for Recognizing Multi-talker Speech with Permutation Invariant Training
* 5 pages, 6 figures, InterSpeech2017 
  Access Paper or Ask Questions

Very Deep Convolutional Neural Networks for Robust Speech Recognition


Oct 02, 2016
Yanmin Qian, Philip C Woodland

Figure 1 for Very Deep Convolutional Neural Networks for Robust Speech Recognition
Figure 2 for Very Deep Convolutional Neural Networks for Robust Speech Recognition
Figure 3 for Very Deep Convolutional Neural Networks for Robust Speech Recognition
Figure 4 for Very Deep Convolutional Neural Networks for Robust Speech Recognition
* accepted by SLT 2016 
  Access Paper or Ask Questions