Alert button
Picture for Zhao You

Zhao You

Alert button

Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation

Sep 04, 2023
Jiaxu Zhu, Weinan Tong, Yaoxun Xu, Changhe Song, Zhiyong Wu, Zhao You, Dan Su, Dong Yu, Helen Meng

Figure 1 for Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation
Figure 2 for Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation
Figure 3 for Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation
Figure 4 for Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation
Viaarxiv icon

3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition

Apr 14, 2022
Zhao You, Shulin Feng, Dan Su, Dong Yu

Figure 1 for 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition
Figure 2 for 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition
Figure 3 for 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition
Figure 4 for 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition
Viaarxiv icon

SpeechMoE2: Mixture-of-Experts Model with Improved Routing

Nov 23, 2021
Zhao You, Shulin Feng, Dan Su, Dong Yu

Figure 1 for SpeechMoE2: Mixture-of-Experts Model with Improved Routing
Figure 2 for SpeechMoE2: Mixture-of-Experts Model with Improved Routing
Figure 3 for SpeechMoE2: Mixture-of-Experts Model with Improved Routing
Figure 4 for SpeechMoE2: Mixture-of-Experts Model with Improved Routing
Viaarxiv icon

GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio

Jun 13, 2021
Guoguo Chen, Shuzhou Chai, Guanbo Wang, Jiayu Du, Wei-Qiang Zhang, Chao Weng, Dan Su, Daniel Povey, Jan Trmal, Junbo Zhang, Mingjie Jin, Sanjeev Khudanpur, Shinji Watanabe, Shuaijiang Zhao, Wei Zou, Xiangang Li, Xuchen Yao, Yongqing Wang, Yujun Wang, Zhao You, Zhiyong Yan

Figure 1 for GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
Figure 2 for GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
Figure 3 for GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
Figure 4 for GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
Viaarxiv icon

SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts

May 07, 2021
Zhao You, Shulin Feng, Dan Su, Dong Yu

Figure 1 for SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts
Figure 2 for SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts
Figure 3 for SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts
Figure 4 for SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts
Viaarxiv icon

DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition

Oct 28, 2019
Zhao You, Dan Su, Jie Chen, Chao Weng, Dong Yu

Figure 1 for DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition
Figure 2 for DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition
Figure 3 for DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition
Figure 4 for DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition
Viaarxiv icon

Teach an all-rounder with experts in different domains

Jul 09, 2019
Zhao You, Dan Su, Dong Yu

Figure 1 for Teach an all-rounder with experts in different domains
Figure 2 for Teach an all-rounder with experts in different domains
Figure 3 for Teach an all-rounder with experts in different domains
Figure 4 for Teach an all-rounder with experts in different domains
Viaarxiv icon