中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共5条，第1-5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：178/50  |  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  
Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only Data 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 卷号: 29, 页码: 1340-1351
作者:  Bai, Ye;  Yi, Jiangyan;  Tao, Jianhua;  Wen, Zhengqi;  Tian, Zhengkun;  Zhang, Shuai
收藏  |  浏览/下载：163/0  |  提交时间：2021/06/07
End-to-End  language modeling  speech recognition  teacher-student learning  transfer learning  
Deep imitator: handwriting calligraphy imitation via deep attention networks 期刊论文
Pattern Recogniton, 2019, 期号: 已接收, 页码: 已接收
作者:  Zhao, Bocheng;  Tao, Jianhua;  Yang, Minghao;  Tian, Zhengkun;  Fan, Cunhang;  Bai, Ye
浏览  |  Adobe PDF(2498Kb)  |  收藏  |  浏览/下载：434/167  |  提交时间：2020/01/05
calligraphy imitation, attention, mata-style matrix, condition Gated Recurrent Unit  
A Public Chinese Dataset for Language Model Adaptation 期刊论文
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2019, 页码: 13
作者:  Bai, Ye;  Yi, Jiangyan;  Tao, Jianhua;  Wen, Zhengqi;  Fan, Cunhang
收藏  |  浏览/下载：271/0  |  提交时间：2019/12/16
Chinese dataset  Language model adaptation  Speech recognition  N-gram  RNNLM  
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
浏览  |  Adobe PDF(907Kb)  |  收藏  |  浏览/下载：400/84  |  提交时间：2019/07/12
Adversarial training  transfer learning  cross-lingual  low-resource  speech recognition