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4条，第1-4条 帮助

限定条件        
已选(0)清除 条数/页：   排序方式：
Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT 期刊论文
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021, 期号: 29, 页码: 1897 - 1911
作者:  Ye Bai;  Jiangyan Yi;  Jianhua Tao;  Zhengkun Tian;  Zhengqi Wen;  Shuai Zhang
Adobe PDF(1163Kb)  |  收藏  |  浏览/下载：175/49  |  提交时间：2021/06/25
端到端语音识别、迁移学习、知识蒸馏、老师-学生学习、BERT、非自回归语音识别  
Adversarial Multilingual Training for Low-Resource Speech Recognition 会议论文
, Calgary, AB, Canada, 2018.04.15-2018.04.20
作者:  Jiangyan Yi;  Jianhua Tao;  Zhengqi Wen;  Ye Bai
Adobe PDF(1343Kb)  |  收藏  |  浏览/下载：31/14  |  提交时间：2020/10/22
CTC Regularized Model Adaptation for Improving LSTM RNN Based Multi-Accent Mandarin Speech Recognition 期刊论文
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2018, 卷号: 90, 期号: 7, 页码: 985-997
作者:  Jiangyan Yi;  Zhengqi Wen;  Jianhua Tao;  Hao Ni;  Bin Liu
Adobe PDF(1416Kb)  |  收藏  |  浏览/下载：127/50  |  提交时间：2020/10/22
multi-accent, Mandarin speech recognition,LSTM-RNN-CTC, model adaptation, CTC regularization  
Language-Adversarial Transfer Learning for Low-Resource Speech Recognition 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2019, 卷号: 27, 期号: 3, 页码: 621-630
作者:  Yi, Jiangyan;  Tao, Jianhua;  Wen, Zhengqi;  Bai, Ye
Adobe PDF(907Kb)  |  收藏  |  浏览/下载：374/83  |  提交时间：2019/07/12
Adversarial training  transfer learning  cross-lingual  low-resource  speech recognition