CASIA OpenIR

Browse/Search Results:  1-10 of 41 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
Deep Time Delay Neural Network for Speech Enhancement with Full Data Learning 会议论文
, Hong Kong, 24-27 Jan. 2021
Authors:  Fan, Cunhang;  Liu, Bin;  Tao, Jianhua;  Yi, Jiangyan;  Wen, Zhengqi;  Song, Leichao
Adobe PDF(934Kb)  |  Favorite  |  View/Download:17/0  |  Submit date:2021/06/01
Gated Recurrent Fusion With Joint Training Framework for Robust End-to-End Speech Recognition 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 期号: 29, 页码: 198-209
Authors:  Fan, Cunhang;  Yi, Jiangyan;  Tao, Jianhua;  Tian, Zhengkun;  Liu, Bin;  Wen, Zhengqi
Adobe PDF(2534Kb)  |  Favorite  |  View/Download:34/2  |  Submit date:2021/03/08
Speech enhancement  Speech recognition  Training  Noise measurement  Logic gates  Acoustic distortion  Task analysis  Gated recurrent fusion  robust end-to-end speech recognition  speech distortion  speech enhancement  speech transformer  
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
Authors:  Bai, Ye;  Yi, Jiangyan;  Tao, Jianhua;  Wen, Zhengqi;  Tian, Zhengkun;  Zhang, Shuai
Favorite  |  View/Download:8/0  |  Submit date:2021/06/07
End-to-End  language modeling  speech recognition  teacher-student learning  transfer learning  
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
Authors:  Ye Bai;  Jiangyan Yi;  Jianhua Tao;  Zhengkun Tian;  Zhengqi Wen;  Shuai Zhang
Adobe PDF(1163Kb)  |  Favorite  |  View/Download:14/0  |  Submit date: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  
Joint Training for Simultaneous Speech Denoising and Dereverberation with Deep Embedding Representations 会议论文
, Shanghai, China, October 25–29, 2020
Authors:  Fan, Cunhang;  Tao, Jianhua;  Liu, Bin;  Yi, Jiangyan;  Wen, Zhengqi
Adobe PDF(158Kb)  |  Favorite  |  View/Download:11/2  |  Submit date:2021/06/01
Gated Recurrent Fusion of Spatial and Spectral Features for Multi-channel Speech Separation with Deep Embedding Representations 会议论文
, Shanghai, China, October 25–29, 2020
Authors:  Fan, Cunhang;  Tao, Jianhua;  Liu, Bin;  Yi, Jiangyan;  Wen, Zhengqi
Adobe PDF(260Kb)  |  Favorite  |  View/Download:12/0  |  Submit date:2021/06/01
FOCUSING ON ATTENTION: PROSODY TRANSFER AND ADAPTATIVE OPTIMIZATION STRATEGY FOR MULTI-SPEAKER END-TO-END SPEECH SYNTHESIS 会议论文
, 网上虚拟会议, 2020-5
Authors:  Fu, Ruibo;  Tao, Jianhua;  Wen, Zhengqi;  Yi, Jiangyan;  Wang, Tao
View  |  Adobe PDF(154Kb)  |  Favorite  |  View/Download:136/53  |  Submit date:2020/06/27
prosody transfer  optimization strategy  speaker adaptation  attention  speech synthesis  
语音伪造与鉴伪的发展与挑战 期刊论文
信息安全学报, 2020, 卷号: 5, 期号: 2, 页码: 28-38
Authors:  陶建华;  傅睿博;  易江燕;  王成龙;  汪涛
View  |  Adobe PDF(432Kb)  |  Favorite  |  View/Download:218/50  |  Submit date:2020/06/27
语音伪造  语音鉴伪  发展与挑战  
Focal Loss for Punctuation Prediction 会议论文
, 北京,中国, 2020.10.25-2020.10.29
Authors:  Jiangyan Yi;  Jianhua Tao;  Zhengkun Tian;  Ye Bai;  Cunhang Fan
View  |  Adobe PDF(247Kb)  |  Favorite  |  View/Download:23/6  |  Submit date:2020/10/22
Synchronous Transformers for end-to-end Speech Recognition 会议论文
, Barcelona, Spain, 2020.05.04-2020.05.08
Authors:  Zhengkun Tian;  Jiangyan Yi;  Ye Bai;  Jianhua Tao;  Shuai Zhang;  Zhengqi Wen
View  |  Adobe PDF(496Kb)  |  Favorite  |  View/Download:21/3  |  Submit date:2020/10/22