中文版 | English

在结果中检索

CASIA OpenIR
（本次检索基于用户作品认领结果）

浏览/检索结果: 共16条，第1-10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：138/52  |  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：165/47  |  提交时间：2023/05/29
Automatic Speech Recognition  Context Biasing  Speech Recognition Customization  Continuous Integrate-and-Fire Mechanism  
CIF-Based Collaborative Decoding for End-to-End Contextual Speech Recognition 会议论文
, Toronto, Canada, 2021-06-06
作者:  Minglun Han;  Linhao Dong;  Shiyu Zhou;  Bo Xu
Adobe PDF(469Kb)  |  收藏  |  浏览/下载：124/37  |  提交时间：2023/05/29
Contextual Speech Recognition  Automatic Speech Recognition  Context Biasing  
Exploring wav2vec 2.0 on speaker verification and language identification 会议论文
, 线上会议, 2021-8-30
作者:  Fan ZY(范志赟);  Li M(李蒙);  Zhou SY(周世玉);  Xu B(徐波)
Adobe PDF(2081Kb)  |  收藏  |  浏览/下载：165/31  |  提交时间：2022/09/17
self-supervised  speaker verification  language identification  multi-task learning  wav2vec 2.0  
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：165/44  |  提交时间：2022/09/17
pre-training  speech recognition  encoder-decoder  sequence-to-sequence  
SPEAKER-AWARE SPEECH-TRANSFORMER 会议论文
, 新加坡, 2019-12-14
作者:  Fan ZY(范志赟);  Li J(李杰);  Zhou SY(周世玉);  Xu B(徐波)
Adobe PDF(361Kb)  |  收藏  |  浏览/下载：154/52  |  提交时间：2022/09/17
Speech-Transformer, speaker adaptation, end-to-end speech recognition, speaker aware training, i-vector  
An End-to-end Structure with CTC Encoder and OCD Decoder For Speech Recognition 会议论文
, Graz, Austria, 2019-9
作者:  Cheng, Yi;  Feng, Wang;  Bo, Xu
Adobe PDF(604Kb)  |  收藏  |  浏览/下载：111/31  |  提交时间：2021/06/21
end-to-end, streaming ASR, encoder-decoder, OCD, CTC  
Towards end-to-end speech recognition for Chinese Mandarin using long short-term memory recurrent neural networks 会议论文
INTERSPEECH 2015 emphasizes an interdisciplinary approach covering all aspects of speech science and technology spanning basic theories to applications. In addition to regular oral and poster sessions, the conference will also feature plenary talks by internationally renowned experts, tutorials, special sessions, show & tell sessions, and exhibits. A number of satellite events will take place immediately before and after the conference., 德国, 2015年
作者:  Li J(李杰);  Zhang H(张恒);  Cai XY(蔡新元);  Xu B(徐波)
收藏  |  浏览/下载：37/0  |  提交时间：2020/10/27
Towards End-to-End Speech Recognition for Chinese Mandarin using Long Short-Term Memory Recurrent Neural Networks 会议论文
Interspeech 2015, Dersen,German, 2016.9.6-2016.9.10
作者:  Jie Li;  Heng Zhang;  Xinyuan Cai;  Bo Xu
收藏  |  浏览/下载：67/0  |  提交时间：2020/10/27
Long Short-term Memory  End-to-end  Connectionist Temporal Classification  Speech Recognition  
A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese 会议论文
ICONIP, Siem Reap, Cambodia, 2018
作者:  Shiyu Zhou;  Linhao Dong;  Shuang Xu;  Bo Xu
收藏  |  浏览/下载：78/0  |  提交时间：2020/10/27
Asr  Multi-head Attention  Modeling Units  Sequence-to-sequence  Transformer