CASIA OpenIR

Browse/Search Results:  1-10 of 51 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
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
Authors:  Yi, Jiangyan;  Tao, Jianhua;  Wen, Zhengqi;  Bai, Ye
Favorite  |  View/Download:10/0  |  Submit date:2019/07/12
Adversarial training  transfer learning  cross-lingual  low-resource  speech recognition  
BLSTM-CRF Based End-to-End Prosodic Boundary Prediction with Context Sensitive Embeddings in A Text-to-Speech Front-End 会议论文
, Hyderabad, 2-6 September 2018
Authors:  Yibin Zheng;  Jianhua Tao;  Zhengqi Wen;  Ya Li
View  |  Adobe PDF(642Kb)  |  Favorite  |  View/Download:50/13  |  Submit date:2019/05/02
Prosodic Boundary Prediction  Blstm-crf  Attention  Context Sensitive Embeddings  End-to-end  
On The Application and Compression of Deep Time Delay Neural Network for Embedded Statistical Parametric Speech Synthesis 会议论文
, Hyderabad, 2-6 September 2018
Authors:  Yibin Zheng;  Jianhua Tao;  Zhengqi Wen;  Ruibo Fu
View  |  Adobe PDF(531Kb)  |  Favorite  |  View/Download:28/10  |  Submit date:2019/05/02
Investigating Deep Neural Network Adaptation for Generating Exclamatory and Interrogative Speech in Mandarin 期刊论文
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2018, 卷号: 90, 期号: 7, 页码: 1039-1052
Authors:  Zheng, Yibin;  Li, Ya;  Wen, Zhengqi;  Liu, Bin;  Tao, Jianhua;  Jianhua Tao
View  |  Adobe PDF(1339Kb)  |  Favorite  |  View/Download:116/25  |  Submit date:2018/01/04
Speech Synthesis  Excitation Parameters  Deep Neural Network Adaptation  Exclamatory Speech  Interrogative Speech  
Improving Deep Neural Network Based Speech Synthesis through Contextual Feature Parametrization and Multi-Task Learning 期刊论文
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2018, 卷号: 90, 期号: 7, 页码: 1025-1037
Authors:  Wen, Zhengqi;  Li, Kehuang;  Huang, Zhen;  Lee, Chin-Hui;  Tao, Jianhua;  Zhengqi Wen
View  |  Adobe PDF(995Kb)  |  Favorite  |  View/Download:85/26  |  Submit date:2018/01/05
Dnn-based Speech Synthesis  Vocoder  Speech Parametrization  Blstm  Phoneme Embedded Vector  Multi-task Learning  Pitch-scaled Spectrum  
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
Authors:  Yi, Jiangyan;  Wen, Zhengqi;  Tao, Jianhua;  Ni, Hao;  Liu, Bin;  Wen ZQ(温正棋)
View  |  Adobe PDF(1416Kb)  |  Favorite  |  View/Download:155/48  |  Submit date:2018/01/04
Multi-accent  Mandarin Speech Recognition  Lstm-rnn-ctc  Model Adaptation  Ctc Regularization  
Adversarial Multilingual Training for Low-resource Speech Recognition 会议论文
, Calgary, Alberta, Canada, 15–20 April, 2018
Authors:  Yi JY(易江燕);  Tao Jianhua;  Wen Zhengqi;  Bai Ye
Adobe PDF(1343Kb)  |  Favorite  |  View/Download:130/10  |  Submit date:2018/05/06
Speech Recognition  Low-resource  Deep Neural Networks  Bottleneck Features  Adversarial Multilingual Training  
基于迁移学习的鲁棒语音识别声学建模方法 期刊论文
清华大学学报, 2018, 卷号: 58, 期号: 1, 页码: 55-60
Authors:  易江燕;  陶建华;  刘斌;  温正棋
View  |  Adobe PDF(1412Kb)  |  Favorite  |  View/Download:115/32  |  Submit date:2018/01/04
鲁棒语音识别  声学模型  神经网络  迁移学习  
基于注意力的端到端韵律结构和重音联合预测方法 会议论文
, 中国连云港, 2017 年10 月
Authors:  郑艺斌;  陶建华;  李雅;  温正棋;  刘斌
View  |  Adobe PDF(710Kb)  |  Favorite  |  View/Download:138/49  |  Submit date:2018/01/04
The NLPR Speech Synthesis entry for Blizzard Challenge 2017 会议论文
, Stockholm, Sweden, 2017.8.25
Authors:  Jianhua Tao;  Ruibo Fu;  Yibin Zheng;  Zhengqi Wen;  Ya Li;  Biu Liu
View  |  Adobe PDF(801Kb)  |  Favorite  |  View/Download:85/12  |  Submit date:2018/01/05