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 Jinyu Li

Jinyu Li

Self-Supervised Learning for speech recognition with Intermediate layer supervision


Dec 16, 2021
Chengyi Wang, Yu Wu, Sanyuan Chen, Shujie Liu, Jinyu Li, Yao Qian, Zhenglu Yang

Figure 1 for Self-Supervised Learning for speech recognition with Intermediate layer supervision
Figure 2 for Self-Supervised Learning for speech recognition with Intermediate layer supervision
Figure 3 for Self-Supervised Learning for speech recognition with Intermediate layer supervision
Figure 4 for Self-Supervised Learning for speech recognition with Intermediate layer supervision
* Submitted to ICASSP 2022 
  Access Paper or Ask Questions

Sequence-level self-learning with multiple hypotheses


Dec 10, 2021
Kenichi Kumatani, Dimitrios Dimitriadis, Yashesh Gaur, Robert Gmyr, Sefik Emre Eskimez, Jinyu Li, Michael Zeng

Figure 1 for Sequence-level self-learning with multiple hypotheses
Figure 2 for Sequence-level self-learning with multiple hypotheses
Figure 3 for Sequence-level self-learning with multiple hypotheses
Figure 4 for Sequence-level self-learning with multiple hypotheses
* Published in Interspeech 2020: https://www.isca-speech.org/archive_v0/Interspeech_2020/pdfs/2020.pdf 
  Access Paper or Ask Questions

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

Recent Advances in End-to-End Automatic Speech Recognition


Nov 02, 2021
Jinyu Li

Figure 1 for Recent Advances in End-to-End Automatic Speech Recognition
Figure 2 for Recent Advances in End-to-End Automatic Speech Recognition
Figure 3 for Recent Advances in End-to-End Automatic Speech Recognition
Figure 4 for Recent Advances in End-to-End Automatic Speech Recognition
* invited paper submitted to APSIPA Transactions on Signal and Information Processing 
  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

Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction


Oct 28, 2021
Heming Wang, Yao Qian, Xiaofei Wang, Yiming Wang, Chengyi Wang, Shujie Liu, Takuya Yoshioka, Jinyu Li, DeLiang Wang

Figure 1 for Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction
Figure 2 for Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction
Figure 3 for Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction
Figure 4 for Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction
* 5 pages, 1 figure, submitted to ICASSP 2022 
  Access Paper or Ask Questions

Continuous Speech Separation with Recurrent Selective Attention Network


Oct 28, 2021
Yixuan Zhang, Zhuo Chen, Jian Wu, Takuya Yoshioka, Peidong Wang, Zhong Meng, Jinyu Li

Figure 1 for Continuous Speech Separation with Recurrent Selective Attention Network
Figure 2 for Continuous Speech Separation with Recurrent Selective Attention Network
Figure 3 for Continuous Speech Separation with Recurrent Selective Attention Network
Figure 4 for Continuous Speech Separation with Recurrent Selective Attention Network
* Submitted to ICASSP 2022 
  Access Paper or Ask Questions

Factorized Neural Transducer for Efficient Language Model Adaptation


Oct 18, 2021
Xie Chen, Zhong Meng, Sarangarajan Parthasarathy, Jinyu Li

Figure 1 for Factorized Neural Transducer for Efficient Language Model Adaptation
Figure 2 for Factorized Neural Transducer for Efficient Language Model Adaptation
Figure 3 for Factorized Neural Transducer for Efficient Language Model Adaptation
Figure 4 for Factorized Neural Transducer for Efficient Language Model Adaptation

  Access Paper or Ask Questions

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


Oct 14, 2021
Zhong Meng, Yashesh Gaur, Naoyuki Kanda, Jinyu Li, Xie Chen, Yu Wu, Yifan Gong

Figure 1 for Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition
Figure 2 for Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition
* 5 pages, submitted to ICASSP 2022 
  Access Paper or Ask Questions

SpeechT5: Unified-Modal Encoder-Decoder Pre-training for Spoken Language Processing


Oct 14, 2021
Junyi Ao, Rui Wang, Long Zhou, Shujie Liu, Shuo Ren, Yu Wu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, Furu Wei

Figure 1 for SpeechT5: Unified-Modal Encoder-Decoder Pre-training for Spoken Language Processing
Figure 2 for SpeechT5: Unified-Modal Encoder-Decoder Pre-training for Spoken Language Processing
Figure 3 for SpeechT5: Unified-Modal Encoder-Decoder Pre-training for Spoken Language Processing
Figure 4 for SpeechT5: Unified-Modal Encoder-Decoder Pre-training for Spoken Language Processing
* work in process 
  Access Paper or Ask Questions

UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training


Oct 12, 2021
Sanyuan Chen, Yu Wu, Chengyi Wang, Zhengyang Chen, Zhuo Chen, Shujie Liu, Jian Wu, Yao Qian, Furu Wei, Jinyu Li, Xiangzhan Yu

Figure 1 for UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training
Figure 2 for UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training
Figure 3 for UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training
Figure 4 for UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training
* ICASSP 2022 Submission 
  Access Paper or Ask Questions

Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition


Oct 11, 2021
Yiming Wang, Jinyu Li, Heming Wang, Yao Qian, Chengyi Wang, Yu Wu

Figure 1 for Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition
Figure 2 for Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition
Figure 3 for Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition
Figure 4 for Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition
* 5 pages, 1 figure, submitted to ICASSP 2022 
  Access Paper or Ask Questions

Have best of both worlds: two-pass hybrid and E2E cascading framework for speech recognition


Oct 10, 2021
Guoli Ye, Vadim Mazalov, Jinyu Li, Yifan Gong

Figure 1 for Have best of both worlds: two-pass hybrid and E2E cascading framework for speech recognition
Figure 2 for Have best of both worlds: two-pass hybrid and E2E cascading framework for speech recognition
Figure 3 for Have best of both worlds: two-pass hybrid and E2E cascading framework for speech recognition
Figure 4 for Have best of both worlds: two-pass hybrid and E2E cascading framework for speech recognition

  Access Paper or Ask Questions

Continuous Streaming Multi-Talker ASR with Dual-path Transducers


Sep 17, 2021
Desh Raj, Liang Lu, Zhuo Chen, Yashesh Gaur, Jinyu Li

Figure 1 for Continuous Streaming Multi-Talker ASR with Dual-path Transducers
Figure 2 for Continuous Streaming Multi-Talker ASR with Dual-path Transducers
Figure 3 for Continuous Streaming Multi-Talker ASR with Dual-path Transducers
Figure 4 for Continuous Streaming Multi-Talker ASR with Dual-path Transducers
* Submitted to IEEE ICASSP 2022 
  Access Paper or Ask Questions

A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems


Aug 17, 2021
Xiaoqiang Wang, Yanqing Liu, Sheng Zhao, Jinyu Li

Figure 1 for A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems
Figure 2 for A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems
Figure 3 for A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems
Figure 4 for A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems
* This paper has been accepted by Interspeech 2021 
  Access Paper or Ask Questions

A Configurable Multilingual Model is All You Need to Recognize All Languages


Jul 13, 2021
Long Zhou, Jinyu Li, Eric Sun, Shujie Liu

Figure 1 for A Configurable Multilingual Model is All You Need to Recognize All Languages
Figure 2 for A Configurable Multilingual Model is All You Need to Recognize All Languages
Figure 3 for A Configurable Multilingual Model is All You Need to Recognize All Languages
Figure 4 for A Configurable Multilingual Model is All You Need to Recognize All Languages

  Access Paper or Ask Questions

UniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset


Jul 12, 2021
Chengyi Wang, Yu Wu, Shujie Liu, Jinyu Li, Yao Qian, Kenichi Kumatani, Furu Wei

Figure 1 for UniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset
Figure 2 for UniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset
Figure 3 for UniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset
Figure 4 for UniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset

  Access Paper or Ask Questions

Investigation of Practical Aspects of Single Channel Speech Separation for ASR


Jul 05, 2021
Jian Wu, Zhuo Chen, Sanyuan Chen, Yu Wu, Takuya Yoshioka, Naoyuki Kanda, Shujie Liu, Jinyu Li

Figure 1 for Investigation of Practical Aspects of Single Channel Speech Separation for ASR
Figure 2 for Investigation of Practical Aspects of Single Channel Speech Separation for ASR
Figure 3 for Investigation of Practical Aspects of Single Channel Speech Separation for ASR
* Accepted by Interspeech 2021 
  Access Paper or Ask Questions

Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition


Jun 04, 2021
Zhong Meng, Yu Wu, Naoyuki Kanda, Liang Lu, Xie Chen, Guoli Ye, Eric Sun, Jinyu Li, Yifan Gong

Figure 1 for Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition
Figure 2 for Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition
Figure 3 for Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition
* Interspeech 2021, Brno, Czech Republic 
 * 5 pages, Interspeech 2021 
  Access Paper or Ask Questions

On Addressing Practical Challenges for RNN-Transducer


May 04, 2021
Rui Zhao, Jian Xue, Jinyu Li, Wenning Wei, Lei He, Yifan Gong

Figure 1 for On Addressing Practical Challenges for RNN-Transducer
Figure 2 for On Addressing Practical Challenges for RNN-Transducer
Figure 3 for On Addressing Practical Challenges for RNN-Transducer
Figure 4 for On Addressing Practical Challenges for RNN-Transducer
* 5 pages 
  Access Paper or Ask Questions

Streaming Multi-talker Speech Recognition with Joint Speaker Identification


Apr 05, 2021
Liang Lu, Naoyuki Kanda, Jinyu Li, Yifan Gong

Figure 1 for Streaming Multi-talker Speech Recognition with Joint Speaker Identification
Figure 2 for Streaming Multi-talker Speech Recognition with Joint Speaker Identification
Figure 3 for Streaming Multi-talker Speech Recognition with Joint Speaker Identification
Figure 4 for Streaming Multi-talker Speech Recognition with Joint Speaker Identification
* 5 pages, 2 figures, submitted to Interspeech 2021 
  Access Paper or Ask Questions

Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition


Feb 02, 2021
Zhong Meng, Naoyuki Kanda, Yashesh Gaur, Sarangarajan Parthasarathy, Eric Sun, Liang Lu, Xie Chen, Jinyu Li, Yifan Gong

Figure 1 for Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition
Figure 2 for Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition
* 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada 
 * 5 pages, ICASSP 2021 
  Access Paper or Ask Questions

Streaming end-to-end multi-talker speech recognition


Nov 26, 2020
Liang Lu, Naoyuki Kanda, Jinyu Li, Yifan Gong

Figure 1 for Streaming end-to-end multi-talker speech recognition
Figure 2 for Streaming end-to-end multi-talker speech recognition
Figure 3 for Streaming end-to-end multi-talker speech recognition
Figure 4 for Streaming end-to-end multi-talker speech recognition
* 5 pages, 4 figures 
  Access Paper or Ask Questions

Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition


Nov 03, 2020
Zhong Meng, Sarangarajan Parthasarathy, Eric Sun, Yashesh Gaur, Naoyuki Kanda, Liang Lu, Xie Chen, Rui Zhao, Jinyu Li, Yifan Gong

Figure 1 for Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition
Figure 2 for Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition
Figure 3 for Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition
Figure 4 for Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition
* 2021 IEEE Spoken Language Technology Workshop (SLT) 
 * 8 pages, 2 figures, SLT 2021 
  Access Paper or Ask Questions

On Minimum Word Error Rate Training of the Hybrid Autoregressive Transducer


Oct 23, 2020
Liang Lu, Zhong Meng, Naoyuki Kanda, Jinyu Li, Yifan Gong

Figure 1 for On Minimum Word Error Rate Training of the Hybrid Autoregressive Transducer
Figure 2 for On Minimum Word Error Rate Training of the Hybrid Autoregressive Transducer
Figure 3 for On Minimum Word Error Rate Training of the Hybrid Autoregressive Transducer
Figure 4 for On Minimum Word Error Rate Training of the Hybrid Autoregressive Transducer
* 5 pages, submitted to ICASSP 2021 
  Access Paper or Ask Questions

Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer


Oct 23, 2020
Sanyuan Chen, Yu Wu, Zhuo Chen, Takuya Yoshioka, Shujie Liu, Jinyu Li

Figure 1 for Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer
Figure 2 for Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer
Figure 3 for Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer

  Access Paper or Ask Questions

Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset


Oct 22, 2020
Xie Chen, Yu Wu, Zhenghao Wang, Shujie Liu, Jinyu Li

Figure 1 for Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset
Figure 2 for Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset
Figure 3 for Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset
Figure 4 for Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset
* 5 pages 
  Access Paper or Ask Questions