Human Parity in Speech Recognition

Établi : December 1, 2015

Publications

Afficher par:

- Session-level Language Modeling for Conversational Speech
  
  Wayne Xiong, Lingfeng Wu, Jun Zhang, Andreas Stolcke
  
  Proceedings EMNLP | November 2018
  
  Publication Projet
- The Microsoft 2017 Conversational Speech Recognition System
  
  Wayne Xiong, Lingfeng Wu, Jasha Droppo, Xuedong Huang, Andreas Stolcke
  
  Proc. IEEE ICASSP | April 2018
  
  Publication
- Achieving Human Parity in Conversational Speech Recognition using CNTK and a GPU Farm
  
  Andreas Stolcke, Frank Seide
  
  GPU Technology Conference | March 2018
  
  GPU Technology Conference
  
  Publication
- Toward Human Parity in Conversational Speech Recognition
  
  Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu, Geoffrey Zweig
  
  IEEE/ACM Transactions on Audio, Speech, and Language Processing | September 2017, Vol 25: pp. 2410-2423
  
  Publication DOI
- Comparing Human and Machine Errors in Conversational Speech Transcription
  
  Andreas Stolcke, Jasha Droppo
  
  Proc. Interspeech | August 2017
  
  Publication
- The Microsoft 2017 Conversational Speech Recognition System [Technical Report]
  
  Wayne Xiong, Lingfeng Wu, Fil Alleva, Jasha Droppo, Xuedong Huang, Andreas Stolcke
  
  MSR-TR-2017-39 | August 2017
  
  Publication
- Humans versus machines: the case of conversational speech recognition
  
  Andreas Stolcke
  
  July 2017
  
  Invited talk, Afeka Conference for Speech Processing, Tel Aviv
  
  Publication
- Advances in All-Neural Speech Recognition
  
  Geoffrey Zweig, Chengzhu Yu, Jasha Droppo, Andreas Stolcke
  
  Proc. IEEE ICASSP | March 2017
  
  Publication
- The Microsoft 2016 Conversational Speech Recognition System
  
  Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu, Geoffrey Zweig
  
  Proc. IEEE ICASSP | March 2017
  
  Publication
- Achieving Human Parity in Conversational Speech Recognition
  
  Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu, Geoffrey Zweig
  
  MSR-TR-2016-71 (revised) | February 2017
  
  Publication Publication
- Achieving Human Parity in Conversational Speech Recognition
  
  Geoff Zweig, Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu
  
  December 2016
  
  IEEE Spoken Language Technology Workshop
  
  Invited talk, IEEE SLT Workshop
  
  Publication
- Deep Convolutional Neural Networks with Layer-wise Context Expansion and Attention
  
  Dong Yu, Wayne Xiong, Jasha Droppo, Andreas Stolcke, Guoli Ye, Jinyu Li, Geoffrey Zweig
  
  Proc. Interspeech | September 2016
  
  Publication Publication
- Deep Bi-directional Recurrent Networks Over Spectral Windows
  
  Abdelrahman Mohamed, Frank Seide, Dong Yu, Jasha Droppo, Andreas Stolcke, Geoffrey Zweig, Gerald Penn
  
  Proc. IEEE Automatic Speech Recognition and Understanding Workshop | December 2015
  
  Publication
- 1-Bit Stochastic Gradient Descent and Application to Data-Parallel Distributed Training of Speech DNNs
  
  Frank Seide, Hao Fu, Jasha Droppo, Gang Li, Dong Yu
  
  Interspeech 2014 | September 2014
  
  Interspeech 2014
  
  Publication
- On Parallelizability of Stochastic Gradient Descent for Speech DNNs
  
  Frank Seide, Hao Fu, Jasha Droppo, Gang Li, Dong Yu
  
  ICASSP | May 2014
  
  Publication

- Session-level Language Modeling for Conversational Speech
  
  Wayne Xiong, Lingfeng Wu, Jun Zhang, Andreas Stolcke
  
  Proceedings EMNLP | November 2018
  
  Publication Projet
- The Microsoft 2017 Conversational Speech Recognition System
  
  Wayne Xiong, Lingfeng Wu, Jasha Droppo, Xuedong Huang, Andreas Stolcke
  
  Proc. IEEE ICASSP | April 2018
  
  Publication
- Achieving Human Parity in Conversational Speech Recognition using CNTK and a GPU Farm
  
  Andreas Stolcke, Frank Seide
  
  GPU Technology Conference | March 2018
  
  GPU Technology Conference
  
  Publication
- Toward Human Parity in Conversational Speech Recognition
  
  Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu, Geoffrey Zweig
  
  IEEE/ACM Transactions on Audio, Speech, and Language Processing | September 2017, Vol 25: pp. 2410-2423
  
  Publication DOI
- The Microsoft 2017 Conversational Speech Recognition System [Technical Report]
  
  Wayne Xiong, Lingfeng Wu, Fil Alleva, Jasha Droppo, Xuedong Huang, Andreas Stolcke
  
  MSR-TR-2017-39 | August 2017
  
  Publication
- Comparing Human and Machine Errors in Conversational Speech Transcription
  
  Andreas Stolcke, Jasha Droppo
  
  Proc. Interspeech | August 2017
  
  Publication
- Humans versus machines: the case of conversational speech recognition
  
  Andreas Stolcke
  
  July 2017
  
  Invited talk, Afeka Conference for Speech Processing, Tel Aviv
  
  Publication
- The Microsoft 2016 Conversational Speech Recognition System
  
  Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu, Geoffrey Zweig
  
  Proc. IEEE ICASSP | March 2017
  
  Publication
- Advances in All-Neural Speech Recognition
  
  Geoffrey Zweig, Chengzhu Yu, Jasha Droppo, Andreas Stolcke
  
  Proc. IEEE ICASSP | March 2017
  
  Publication
- Achieving Human Parity in Conversational Speech Recognition
  
  Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu, Geoffrey Zweig
  
  MSR-TR-2016-71 (revised) | February 2017
  
  Publication Publication
- Achieving Human Parity in Conversational Speech Recognition
  
  Geoff Zweig, Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu
  
  December 2016
  
  IEEE Spoken Language Technology Workshop
  
  Invited talk, IEEE SLT Workshop
  
  Publication
- Deep Convolutional Neural Networks with Layer-wise Context Expansion and Attention
  
  Dong Yu, Wayne Xiong, Jasha Droppo, Andreas Stolcke, Guoli Ye, Jinyu Li, Geoffrey Zweig
  
  Proc. Interspeech | September 2016
  
  Publication Publication
- Deep Bi-directional Recurrent Networks Over Spectral Windows
  
  Abdelrahman Mohamed, Frank Seide, Dong Yu, Jasha Droppo, Andreas Stolcke, Geoffrey Zweig, Gerald Penn
  
  Proc. IEEE Automatic Speech Recognition and Understanding Workshop | December 2015
  
  Publication
- 1-Bit Stochastic Gradient Descent and Application to Data-Parallel Distributed Training of Speech DNNs
  
  Frank Seide, Hao Fu, Jasha Droppo, Gang Li, Dong Yu
  
  Interspeech 2014 | September 2014
  
  Interspeech 2014
  
  Publication
- On Parallelizability of Stochastic Gradient Descent for Speech DNNs
  
  Frank Seide, Hao Fu, Jasha Droppo, Gang Li, Dong Yu
  
  ICASSP | May 2014
  
  Publication
- On Parallelizability of Stochastic Gradient Descent for Speech DNNs
  
  Frank Seide, Hao Fu, Jasha Droppo, Gang Li, Dong Yu
  
  ICASSP | May 2014
  
  Publication

- Session-level Language Modeling for Conversational Speech
  
  Wayne Xiong, Lingfeng Wu, Jun Zhang, Andreas Stolcke
  
  Proceedings EMNLP | November 2018
  
  Publication Projet
- The Microsoft 2017 Conversational Speech Recognition System
  
  Wayne Xiong, Lingfeng Wu, Jasha Droppo, Xuedong Huang, Andreas Stolcke
  
  Proc. IEEE ICASSP | April 2018
  
  Publication
- Achieving Human Parity in Conversational Speech Recognition using CNTK and a GPU Farm
  
  Andreas Stolcke, Frank Seide
  
  GPU Technology Conference | March 2018
  
  GPU Technology Conference
  
  Publication
- Comparing Human and Machine Errors in Conversational Speech Transcription
  
  Andreas Stolcke, Jasha Droppo
  
  Proc. Interspeech | August 2017
  
  Publication
- The Microsoft 2016 Conversational Speech Recognition System
  
  Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu, Geoffrey Zweig
  
  Proc. IEEE ICASSP | March 2017
  
  Publication
- Advances in All-Neural Speech Recognition
  
  Geoffrey Zweig, Chengzhu Yu, Jasha Droppo, Andreas Stolcke
  
  Proc. IEEE ICASSP | March 2017
  
  Publication
- Deep Convolutional Neural Networks with Layer-wise Context Expansion and Attention
  
  Dong Yu, Wayne Xiong, Jasha Droppo, Andreas Stolcke, Guoli Ye, Jinyu Li, Geoffrey Zweig
  
  Proc. Interspeech | September 2016
  
  Publication Publication
- Deep Bi-directional Recurrent Networks Over Spectral Windows
  
  Abdelrahman Mohamed, Frank Seide, Dong Yu, Jasha Droppo, Andreas Stolcke, Geoffrey Zweig, Gerald Penn
  
  Proc. IEEE Automatic Speech Recognition and Understanding Workshop | December 2015
  
  Publication
- 1-Bit Stochastic Gradient Descent and Application to Data-Parallel Distributed Training of Speech DNNs
  
  Frank Seide, Hao Fu, Jasha Droppo, Gang Li, Dong Yu
  
  Interspeech 2014 | September 2014
  
  Interspeech 2014
  
  Publication
- On Parallelizability of Stochastic Gradient Descent for Speech DNNs
  
  Frank Seide, Hao Fu, Jasha Droppo, Gang Li, Dong Yu
  
  ICASSP | May 2014
  
  Publication
- Toward Human Parity in Conversational Speech Recognition
  
  Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu, Geoffrey Zweig
  
  IEEE/ACM Transactions on Audio, Speech, and Language Processing | September 2017, Vol 25: pp. 2410-2423
  
  Publication DOI
- The Microsoft 2017 Conversational Speech Recognition System [Technical Report]
  
  Wayne Xiong, Lingfeng Wu, Fil Alleva, Jasha Droppo, Xuedong Huang, Andreas Stolcke
  
  MSR-TR-2017-39 | August 2017
  
  Publication
- Achieving Human Parity in Conversational Speech Recognition
  
  Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu, Geoffrey Zweig
  
  MSR-TR-2016-71 (revised) | February 2017
  
  Publication Publication
- Humans versus machines: the case of conversational speech recognition
  
  Andreas Stolcke
  
  July 2017
  
  Invited talk, Afeka Conference for Speech Processing, Tel Aviv
  
  Publication
- Achieving Human Parity in Conversational Speech Recognition
  
  Geoff Zweig, Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Mike Seltzer, Andreas Stolcke, Dong Yu
  
  December 2016
  
  IEEE Spoken Language Technology Workshop
  
  Invited talk, IEEE SLT Workshop
  
  Publication

Human Parity in Speech Recognition

Publications

Session-level Language Modeling for Conversational Speech

The Microsoft 2017 Conversational Speech Recognition System

Achieving Human Parity in Conversational Speech Recognition using CNTK and a GPU Farm

Toward Human Parity in Conversational Speech Recognition

Comparing Human and Machine Errors in Conversational Speech Transcription

The Microsoft 2017 Conversational Speech Recognition System [Technical Report]

Humans versus machines: the case of conversational speech recognition

Advances in All-Neural Speech Recognition

The Microsoft 2016 Conversational Speech Recognition System

Achieving Human Parity in Conversational Speech Recognition

Achieving Human Parity in Conversational Speech Recognition

Deep Convolutional Neural Networks with Layer-wise Context Expansion and Attention

Deep Bi-directional Recurrent Networks Over Spectral Windows

1-Bit Stochastic Gradient Descent and Application to Data-Parallel Distributed Training of Speech DNNs

On Parallelizability of Stochastic Gradient Descent for Speech DNNs

Session-level Language Modeling for Conversational Speech

The Microsoft 2017 Conversational Speech Recognition System

Achieving Human Parity in Conversational Speech Recognition using CNTK and a GPU Farm

Toward Human Parity in Conversational Speech Recognition

The Microsoft 2017 Conversational Speech Recognition System [Technical Report]

Comparing Human and Machine Errors in Conversational Speech Transcription

Humans versus machines: the case of conversational speech recognition

The Microsoft 2016 Conversational Speech Recognition System

Advances in All-Neural Speech Recognition

Achieving Human Parity in Conversational Speech Recognition

Achieving Human Parity in Conversational Speech Recognition

Deep Convolutional Neural Networks with Layer-wise Context Expansion and Attention

Deep Bi-directional Recurrent Networks Over Spectral Windows

1-Bit Stochastic Gradient Descent and Application to Data-Parallel Distributed Training of Speech DNNs

On Parallelizability of Stochastic Gradient Descent for Speech DNNs

On Parallelizability of Stochastic Gradient Descent for Speech DNNs

Session-level Language Modeling for Conversational Speech

The Microsoft 2017 Conversational Speech Recognition System

Achieving Human Parity in Conversational Speech Recognition using CNTK and a GPU Farm

Comparing Human and Machine Errors in Conversational Speech Transcription

The Microsoft 2016 Conversational Speech Recognition System

Advances in All-Neural Speech Recognition

Deep Convolutional Neural Networks with Layer-wise Context Expansion and Attention

Deep Bi-directional Recurrent Networks Over Spectral Windows

1-Bit Stochastic Gradient Descent and Application to Data-Parallel Distributed Training of Speech DNNs

On Parallelizability of Stochastic Gradient Descent for Speech DNNs

Toward Human Parity in Conversational Speech Recognition

The Microsoft 2017 Conversational Speech Recognition System [Technical Report]

Achieving Human Parity in Conversational Speech Recognition

Humans versus machines: the case of conversational speech recognition

Achieving Human Parity in Conversational Speech Recognition