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 Yonghui Wu

Yonghui Wu

Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling


Apr 13, 2021
Isaac Elias, Heiga Zen, Jonathan Shen, Yu Zhang, Ye Jia, RJ Skerry-Ryan, Yonghui Wu

Figure 1 for Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
Figure 2 for Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
Figure 3 for Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
Figure 4 for Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
* Submitted to INTERSPEECH 2021 
  Access Paper or Ask Questions

PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS


Apr 02, 2021
Ye Jia, Heiga Zen, Jonathan Shen, Yu Zhang, Yonghui Wu

Figure 1 for PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS
Figure 2 for PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS
Figure 3 for PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS
Figure 4 for PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS
* Submitted to Interspeech 2021 
  Access Paper or Ask Questions

Improving Longer-range Dialogue State Tracking


Feb 27, 2021
Ye Zhang, Yuan Cao, Mahdis Mahdieh, Jefferey Zhao, Yonghui Wu

Figure 1 for Improving Longer-range Dialogue State Tracking
Figure 2 for Improving Longer-range Dialogue State Tracking
Figure 3 for Improving Longer-range Dialogue State Tracking
Figure 4 for Improving Longer-range Dialogue State Tracking
* 10 pages 
  Access Paper or Ask Questions

Distilling Interpretable Models into Human-Readable Code


Feb 09, 2021
Walker Ravina, Ethan Sterling, Olexiy Oryeshko, Nathan Bell, Honglei Zhuang, Xuanhui Wang, Yonghui Wu, Alexander Grushetsky

Figure 1 for Distilling Interpretable Models into Human-Readable Code
Figure 2 for Distilling Interpretable Models into Human-Readable Code
Figure 3 for Distilling Interpretable Models into Human-Readable Code
Figure 4 for Distilling Interpretable Models into Human-Readable Code
* 13 pages, Latex; Updated the introduction and preliminaries sections; Updated some figures for greater clarity and brevity; Added a new dataset to the experiments; Added a more detailed table of experiment results; Added a discussion of distillation failures to the experiments relating to the new dataset 
  Access Paper or Ask Questions

FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization


Oct 21, 2020
Jiahui Yu, Chung-Cheng Chiu, Bo Li, Shuo-yiin Chang, Tara N. Sainath, Yanzhang He, Arun Narayanan, Wei Han, Anmol Gulati, Yonghui Wu, Ruoming Pang

Figure 1 for FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization
Figure 2 for FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization
Figure 3 for FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization
Figure 4 for FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization
* tech report 
  Access Paper or Ask Questions

Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition


Oct 20, 2020
Yu Zhang, James Qin, Daniel S. Park, Wei Han, Chung-Cheng Chiu, Ruoming Pang, Quoc V. Le, Yonghui Wu

Figure 1 for Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
Figure 2 for Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
Figure 3 for Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
Figure 4 for Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
* 11 pages, 3 figures, 5 tables. Submitted to NeurIPS SAS 2020 Workshop 
  Access Paper or Ask Questions

Universal ASR: Unify and Improve Streaming ASR with Full-context Modeling


Oct 12, 2020
Jiahui Yu, Wei Han, Anmol Gulati, Chung-Cheng Chiu, Bo Li, Tara N. Sainath, Yonghui Wu, Ruoming Pang

Figure 1 for Universal ASR: Unify and Improve Streaming ASR with Full-context Modeling
Figure 2 for Universal ASR: Unify and Improve Streaming ASR with Full-context Modeling
Figure 3 for Universal ASR: Unify and Improve Streaming ASR with Full-context Modeling
Figure 4 for Universal ASR: Unify and Improve Streaming ASR with Full-context Modeling
* tech report 
  Access Paper or Ask Questions

Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling


Oct 08, 2020
Jonathan Shen, Ye Jia, Mike Chrzanowski, Yu Zhang, Isaac Elias, Heiga Zen, Yonghui Wu

Figure 1 for Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling
Figure 2 for Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling
Figure 3 for Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling
Figure 4 for Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling
* Under review as a conference paper at ICLR 2021 
  Access Paper or Ask Questions

Improved Noisy Student Training for Automatic Speech Recognition


May 19, 2020
Daniel S. Park, Yu Zhang, Ye Jia, Wei Han, Chung-Cheng Chiu, Bo Li, Yonghui Wu, Quoc V. Le

Figure 1 for Improved Noisy Student Training for Automatic Speech Recognition
Figure 2 for Improved Noisy Student Training for Automatic Speech Recognition
Figure 3 for Improved Noisy Student Training for Automatic Speech Recognition
Figure 4 for Improved Noisy Student Training for Automatic Speech Recognition
* 5 pages, 5 figures, 4 tables. Submitted to Interspeech 2020 
  Access Paper or Ask Questions

RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions


May 17, 2020
Chung-Cheng Chiu, Arun Narayanan, Wei Han, Rohit Prabhavalkar, Yu Zhang, Navdeep Jaitly, Ruoming Pang, Tara N. Sainath, Patrick Nguyen, Liangliang Cao, Yonghui Wu

Figure 1 for RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions
Figure 2 for RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions
Figure 3 for RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions
Figure 4 for RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions
* Submitted to Interspeech 2020 
  Access Paper or Ask Questions

Conformer: Convolution-augmented Transformer for Speech Recognition


May 16, 2020
Anmol Gulati, James Qin, Chung-Cheng Chiu, Niki Parmar, Yu Zhang, Jiahui Yu, Wei Han, Shibo Wang, Zhengdong Zhang, Yonghui Wu, Ruoming Pang

Figure 1 for Conformer: Convolution-augmented Transformer for Speech Recognition
Figure 2 for Conformer: Convolution-augmented Transformer for Speech Recognition
Figure 3 for Conformer: Convolution-augmented Transformer for Speech Recognition
Figure 4 for Conformer: Convolution-augmented Transformer for Speech Recognition
* Submitted to Interspeech 2020 
  Access Paper or Ask Questions

ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context


May 16, 2020
Wei Han, Zhengdong Zhang, Yu Zhang, Jiahui Yu, Chung-Cheng Chiu, James Qin, Anmol Gulati, Ruoming Pang, Yonghui Wu

Figure 1 for ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
Figure 2 for ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
Figure 3 for ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
Figure 4 for ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
* Submitted to Interspeech 2020 
  Access Paper or Ask Questions

Interpretable Learning-to-Rank with Generalized Additive Models


May 14, 2020
Honglei Zhuang, Xuanhui Wang, Michael Bendersky, Alexander Grushetsky, Yonghui Wu, Petr Mitrichev, Ethan Sterling, Nathan Bell, Walker Ravina, Hai Qian

Figure 1 for Interpretable Learning-to-Rank with Generalized Additive Models
Figure 2 for Interpretable Learning-to-Rank with Generalized Additive Models
Figure 3 for Interpretable Learning-to-Rank with Generalized Additive Models
Figure 4 for Interpretable Learning-to-Rank with Generalized Additive Models
* 10 pages 
  Access Paper or Ask Questions

Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation


May 11, 2020
Aditya Siddhant, Ankur Bapna, Yuan Cao, Orhan Firat, Mia Chen, Sneha Kudugunta, Naveen Arivazhagan, Yonghui Wu

Figure 1 for Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation
Figure 2 for Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation
Figure 3 for Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation
Figure 4 for Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation
* ACL 2020 
  Access Paper or Ask Questions

A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency


Mar 28, 2020
Tara N. Sainath, Yanzhang He, Bo Li, Arun Narayanan, Ruoming Pang, Antoine Bruguier, Shuo-yiin Chang, Wei Li, Raziel Alvarez, Zhifeng Chen, Chung-Cheng Chiu, David Garcia, Alex Gruenstein, Ke Hu, Minho Jin, Anjuli Kannan, Qiao Liang, Ian McGraw, Cal Peyser, Rohit Prabhavalkar, Golan Pundak, David Rybach, Yuan Shangguan, Yash Sheth, Trevor Strohman, Mirko Visontai, Yonghui Wu, Yu Zhang, Ding Zhao

Figure 1 for A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
Figure 2 for A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
Figure 3 for A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
Figure 4 for A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
* In Proceedings of IEEE ICASSP 2020 
  Access Paper or Ask Questions

Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis


Feb 06, 2020
Guangzhi Sun, Yu Zhang, Ron J. Weiss, Yuan Cao, Heiga Zen, Yonghui Wu

Figure 1 for Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis
Figure 2 for Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis
Figure 3 for Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis
Figure 4 for Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis
* to appear in ICASSP 2020 
  Access Paper or Ask Questions

Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior


Feb 06, 2020
Guangzhi Sun, Yu Zhang, Ron J. Weiss, Yuan Cao, Heiga Zen, Andrew Rosenberg, Bhuvana Ramabhadran, Yonghui Wu

Figure 1 for Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior
Figure 2 for Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior
Figure 3 for Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior
Figure 4 for Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior
* To appear in ICASSP 2020 
  Access Paper or Ask Questions

SpecAugment on Large Scale Datasets


Dec 11, 2019
Daniel S. Park, Yu Zhang, Chung-Cheng Chiu, Youzheng Chen, Bo Li, William Chan, Quoc V. Le, Yonghui Wu

Figure 1 for SpecAugment on Large Scale Datasets
Figure 2 for SpecAugment on Large Scale Datasets
Figure 3 for SpecAugment on Large Scale Datasets
* 5 pages, 3 tables; submitted to ICASSP 2020 
  Access Paper or Ask Questions

A comparison of end-to-end models for long-form speech recognition


Nov 06, 2019
Chung-Cheng Chiu, Wei Han, Yu Zhang, Ruoming Pang, Sergey Kishchenko, Patrick Nguyen, Arun Narayanan, Hank Liao, Shuyuan Zhang, Anjuli Kannan, Rohit Prabhavalkar, Zhifeng Chen, Tara Sainath, Yonghui Wu

Figure 1 for A comparison of end-to-end models for long-form speech recognition
Figure 2 for A comparison of end-to-end models for long-form speech recognition
Figure 3 for A comparison of end-to-end models for long-form speech recognition
* ASRU camera-ready version 
  Access Paper or Ask Questions

Identifying Cancer Patients at Risk for Heart Failure Using Machine Learning Methods


Oct 01, 2019
Xi Yang, Yan Gong, Nida Waheed, Keith March, Jiang Bian, William R. Hogan, Yonghui Wu

Figure 1 for Identifying Cancer Patients at Risk for Heart Failure Using Machine Learning Methods
Figure 2 for Identifying Cancer Patients at Risk for Heart Failure Using Machine Learning Methods
Figure 3 for Identifying Cancer Patients at Risk for Heart Failure Using Machine Learning Methods
Figure 4 for Identifying Cancer Patients at Risk for Heart Failure Using Machine Learning Methods
* 6 pages, 1 figure, 3 tables, accepted by AMIA 2019 
  Access Paper or Ask Questions

Speech Recognition with Augmented Synthesized Speech


Sep 25, 2019
Andrew Rosenberg, Yu Zhang, Bhuvana Ramabhadran, Ye Jia, Pedro Moreno, Yonghui Wu, Zelin Wu

Figure 1 for Speech Recognition with Augmented Synthesized Speech
Figure 2 for Speech Recognition with Augmented Synthesized Speech
Figure 3 for Speech Recognition with Augmented Synthesized Speech
Figure 4 for Speech Recognition with Augmented Synthesized Speech
* Accepted for publication at ASRU 2020 
  Access Paper or Ask Questions

Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model


Sep 11, 2019
Anjuli Kannan, Arindrima Datta, Tara N. Sainath, Eugene Weinstein, Bhuvana Ramabhadran, Yonghui Wu, Ankur Bapna, Zhifeng Chen, Seungji Lee

Figure 1 for Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model
Figure 2 for Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model
Figure 3 for Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model
* Accepted in Interspeech 2019 
  Access Paper or Ask Questions