语音识别，博弈智能，强化学习

081104-模式识别与智能系统

强化学习, 博弈智能, 模式识别

2013-09--2019-01   中国科学院自动化研究所   博士
2007-09--2009-12   浙江大学   硕士
2002-09--2006-06   湖南师范大学   学士

   

（ 1 ） 端到端的在线语音检测与识别方法、系统及设备, 发明专利, 2022, 第 1 作者, 专利号: CN112951213B

（ 2 ） 一种语音文本联合预训练方法及系统, 发明专利, 2022, 第 1 作者, 专利号: 202210346308.6

（ 3 ） 低资源多语言的语音识别模型、语音识别方法, 发明专利, 2019, 第 1 作者, 专利号: CN110428818A

   

[1] 王子翼, 戎奕名, 江德扬, 吴浩然, 周世玉, 徐波. CIEASR: Contextual Image-Enhanced Automatic Speech Recognition for Improved Homophone Discrimination. ACM MM. 2024, 第 5 作者null(null): 
[2] Han, Minglun, Dong, Linhao, Zhou, Shiyu, Xu, Bo, IEEE. CIF-BASED COLLABORATIVE DECODING FOR END-TO-END CONTEXTUAL SPEECH RECOGNITION. 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021). 2021, 第 3 作者6528-6532, 
[3] Yi, Cheng, Zhou, Shiyu, Xu, Bo. Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-Resource Speech Recognition. IEEE SIGNAL PROCESSING LETTERS[J]. 2021, 第 2 作者28: 788-792, http://dx.doi.org/10.1109/LSP.2021.3071668.
[4] Zhiyun Fan, Shiyu Zhou, Bo Xu. TWO-STAGE PRE-TRAINING FOR SEQUENCE TO SEQUENCE SPEECH RECOGNITION. IJCNN[J]. 2021, 第 2 作者
[5] Han, Minglun, Dong, Linhao, Zhou, Shiyu, Xu, Bo, IEEE. CIF-BASED COLLABORATIVE DECODING FOR END-TO-END CONTEXTUAL SPEECH RECOGNITION. 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021). 2021, 第 3 作者6528-6532, 
[6] Yi, Cheng, Zhou, Shiyu, Xu, Bo. Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-Resource Speech Recognition. IEEE SIGNAL PROCESSING LETTERS[J]. 2021, 第 2 作者28: 788-792, http://dx.doi.org/10.1109/LSP.2021.3071668.
[7] Zhiyun Fan, Shiyu Zhou, Bo Xu. TWO-STAGE PRE-TRAINING FOR SEQUENCE TO SEQUENCE SPEECH RECOGNITION. IJCNN[J]. 2021, 第 2 作者
[8] Dong Linhao, Zhou Shiyu, Chen Wei, Xu Bo, Int Speech Commun Assoc. Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin. 19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6. 2018, 第 2 作者816-820, 
[9] Zhou, Shiyu, Dong, Linhao, Xu, Shuang, Xu, Bo, Cheng, L, Leung, ACS, Ozawa, S. A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese. NEURAL INFORMATION PROCESSING (ICONIP 2018), PT V. 2018, 第 11 作者11305: 210-220, 
[10] Shiyu Zhou, Linhao Dong, Shuang Xu, Bo Xu. Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese. INTERSPEECH. 2018, 第 1 作者  通讯作者  http://ir.ia.ac.cn/handle/173211/22392.
[11] Dong Linhao, Zhou Shiyu, Chen Wei, Xu Bo, Int Speech Commun Assoc. Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin. 19th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2018). 2018, 第 2 作者816-820, 
[12] Zhou, Shiyu, Dong, Linhao, Xu, Shuang, Xu, Bo, Cheng, L, Leung, ACS, Ozawa, S. A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese. NEURAL INFORMATION PROCESSING (ICONIP 2018), PT V. 2018, 第 1 作者  通讯作者  11305: 210-220, 
[13] Shiyu Zhou, Linhao Dong, Shuang Xu, Bo Xu. Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese. INTERSPEECH. 2018, 第 11 作者http://ir.ia.ac.cn/handle/173211/22392.
[14] Shuang Xu, Bo Xu, Shiyu Zhou, Yuanyuan Zhao. Word-level Permutation and Improved Lower Frame Rate for RNN-Based Acoustic Modeling. ICONIP2017. 2017, 第 3 作者859-869, http://ir.ia.ac.cn/handle/173211/15429.
[15] Zhou, Shiyu, Zhao, Yuanyuan, Xu, Shuang, Xu, Bo, Int Speech Commun Assoc. Multilingual Recurrent Neural Networks with Residual Learning for Low-Resource Speech Recognition. 18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6. 2017, 第 11 作者704-708, 
[16] Shuang Xu, Bo Xu, Shiyu Zhou, Yuanyuan Zhao. Word-level Permutation and Improved Lower Frame Rate for RNN-Based Acoustic Modeling. ICONIP2017. 2017, 第 3 作者859-869, http://ir.ia.ac.cn/handle/173211/15429.
[17] Zhou, Shiyu, Zhao, Yuanyuan, Xu, Shuang, Xu, Bo, Int Speech Commun Assoc. Multilingual Recurrent Neural Networks with Residual Learning for Low-Resource Speech Recognition. 18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6. 2017, 第 1 作者  通讯作者  704-708, 

现指导学生

戎奕名  硕士研究生  085410-人工智能  

邹雨巷  硕士研究生  081104-模式识别与智能系统

董林昊  博士研究生  081104-模式识别与智能系统

易澄  博士研究生  081104-模式识别与智能系统

范志赟  博士研究生  081104-模式识别与智能系统

韩明伦  博士研究生  081104-模式识别与智能系统