CASIA OpenIR

Browse/Search Results:  1-10 of 52 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
SpecMNet: Spectrum mend network for monaural speech enhancement 期刊论文
APPLIED ACOUSTICS, 2022, 卷号: 194, 页码: 9
Authors:  Fan, Cunhang;  Zhang, Hongmei;  Yi, Jiangyan;  Lv, Zhao;  Tao, Jianhua;  Li, Taihao;  Pei, Guanxiong;  Wu, Xiaopei;  Li, Sheng
Favorite  |  View/Download:22/0  |  Submit date:2022/07/25
Monaural speech enhancement  Speech distortion  Spectrum mend network  SI-SNR  BLSTM  
Hybrid Autoregressive and Non-Autoregressive Transformer Models for Speech Recognition 期刊论文
IEEE SIGNAL PROCESSING LETTERS, 2022, 页码: 762-766
Authors:  Zhengkun Tian;  Jiangyan Yi;  Jianhua Tao;  Shuai Zhang;  Zhengqi Wen
Adobe PDF(934Kb)  |  Favorite  |  View/Download:36/4  |  Submit date:2022/06/14
NeuralDPS: Neural Deterministic Plus Stochastic Model With Multiband Excitation for Noise-Controllable Waveform Generation 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2022, 卷号: 30, 页码: 865-878
Authors:  Wang, Tao;  Fu, Ruibo;  Yi, Jiangyan;  Tao, Jianhua;  Wen, Zhengqi
Favorite  |  View/Download:26/0  |  Submit date:2022/06/06
Vocoders  Stochastic processes  Neural networks  Speech processing  Signal to noise ratio  Acoustics  Speech enhancement  Vocoder  speech synthesis  deterministic plus stochastic  multiband excitation  noise control  
CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editing 期刊论文
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2022, 卷号: 30, 页码: 2241-2254
Authors:  Wang, Tao;  Yi, Jiangyan;  Fu, Ruibo;  Tao, Jianhua;  Wen, Zhengqi
Favorite  |  View/Download:5/0  |  Submit date:2022/09/19
Speech processing  Decoding  Predictive models  Acoustics  Transfer learning  Training  Task analysis  Coarse-to-fine decoding  mask prediction  one-shot learning  text-based speech editing  text-to-speech  
One In A Hundred: Selecting the Best Predicted Sequence from Numerous Candidates for Speech Recognition 会议论文
, Tokyo, Japan, 14-17 December 2021
Authors:  Zhengkun Tian;  Jiangyan Yi;  Ye Bai;  Jianhua Tao;  Shuai Zhang;  Zhengqi Wen
Adobe PDF(563Kb)  |  Favorite  |  View/Download:29/1  |  Submit date:2022/06/14
Continual Learning for Fake Audio Detection 会议论文
, 线上(捷克), 2021-9
Authors:  Ma Haoxin;  Yi Jiangyan;  Tao Jianhua;  Bai Ye;  Tian Zhengkun;  Wang Chenglong
Adobe PDF(2113Kb)  |  Favorite  |  View/Download:46/13  |  Submit date:2022/06/20
fake audio detection  continual learning  detecting fake without forgetting  
FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization 会议论文
, Brno, Czechia, 30 August – 3 September
Authors:  Zhengkun Tian;  Jiangyan Yi;  Ye Bai;  Jianhua Tao;  Shuai Zhang;  Zhengqi Wen
Adobe PDF(839Kb)  |  Favorite  |  View/Download:24/0  |  Submit date:2022/06/14
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:49/3  |  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:96/9  |  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  
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:54/4  |  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