CASIA OpenIR
(本次检索基于用户作品认领结果)

浏览/检索结果: 共8条,第1-8条 帮助

限定条件            
已选(0)清除 条数/页:   排序方式:
Knowledge Transfer from Pre-Trained Language Models to CIF-Based Speech Recognizers via Hierarchical Distillation 会议论文
, Dublin, Ireland, 2023-8-20
作者:  Minglun Han;  Feilong Chen;  Jing Shi;  Shuang Xu;  Bo Xu
Adobe PDF(563Kb)  |  收藏  |  浏览/下载:175/66  |  提交时间:2023/06/20
Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection 会议论文
, Singapore, Singapore, 2022.05
作者:  Minglun Han;  Linhao Dong;  Zhenlin Liang;  Meng Cai;  Shiyu Zhou;  Zejun Ma;  Bo Xu
Adobe PDF(463Kb)  |  收藏  |  浏览/下载:198/55  |  提交时间:2023/05/29
Automatic Speech Recognition  Context Biasing  Speech Recognition Customization  Continuous Integrate-and-Fire Mechanism  
TWO-STAGE PRE-TRAINING FOR SEQUENCE TO SEQUENCE SPEECH RECOGNITION 会议论文
, 线上会议, 2021-7-18
作者:  Fan ZY(范志赟);  Zhou SY(周世玉);  Xu B(徐波)
Adobe PDF(230Kb)  |  收藏  |  浏览/下载:185/49  |  提交时间:2022/09/17
pre-training  speech recognition  encoder-decoder  sequence-to-sequence  
鸡尾酒会问题与相关听觉模型的研究现状与展望 期刊论文
自动化学报, 2019, 卷号: 45, 期号: 2, 页码: 234-251
作者:  黄雅婷;  石晶;  许家铭;  徐波
Adobe PDF(3009Kb)  |  收藏  |  浏览/下载:208/67  |  提交时间:2022/09/17
Consecutive decoding for speech-to-text translation 会议论文
, Virtual, 2021-2
作者:  Dong QQ(董倩倩);  Mingxuan Wang(王明轩);  Hao Zhou(周浩);  Shuang Xu(徐爽);  Bo Xu(徐波);  Lei Li(李磊)
Adobe PDF(586Kb)  |  收藏  |  浏览/下载:230/70  |  提交时间:2021/06/24
Listen, understand and translate: triple supervision decouples end-to-endspeech-to-text translation 会议论文
, Virtual, 2021-2
作者:  Dong QQ(董倩倩);  Rong Ye(叶蓉);  Mingxuan Wang(王明轩);  Hao Zhou(周浩);  Shuang Xu(徐爽);  Bo Xu(徐波);  Lei Li(李磊)
Adobe PDF(991Kb)  |  收藏  |  浏览/下载:208/45  |  提交时间:2021/06/24
CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition 会议论文
, 在线会议, 2020-05
作者:  Dong, Linhao;  Xu, Bo
浏览  |  Adobe PDF(641Kb)  |  收藏  |  浏览/下载:347/77  |  提交时间:2020/06/13
continuous integrate-and-fire  end-to-end model  soft and monotonic alignment  online speech recognition  acoustic boundary positioning  
Speech-Transformer: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition 会议论文
, Calgary, Canada, 2018-04
作者:  Dong, Linhao;  Xu, Shuang;  Xu, Bo
浏览  |  Adobe PDF(640Kb)  |  收藏  |  浏览/下载:849/489  |  提交时间:2020/06/13
speech recognition  sequence-to-sequence  attention  transformer