CASIA OpenIR
(Note: the search results are based on claimed items)

Browse/Search Results:  1-10 of 21 Help

Filters        
Selected(0)Clear Items/Page:    Sort:
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:117/32  |  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:220/86  |  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:161/20  |  Submit date:2018/05/06
Speech Recognition  Low-resource  Deep Neural Networks  Bottleneck Features  Adversarial Multilingual Training  
基于医学影像的语音驱动舌位运动合成 会议论文
, 中国连云港, 2017-10-11~13
Authors:  张大伟;  杨明浩;  陶建华
View  |  Adobe PDF(497Kb)  |  Favorite  |  View/Download:106/14  |  Submit date:2018/01/04
舌位运动合成  语音驱动  医学影像  组合深度神经网络  
Acoustic Model Compression with Knowledge Transfer 会议论文
, 连云港,中国, October 11-13, 2017
Authors:  Yi, Jiangyan;  Tao, Jianhua;  Wen, Zhengqi;  Li, Ya;  Ni,Hao
View  |  Adobe PDF(321Kb)  |  Favorite  |  View/Download:115/23  |  Submit date:2018/01/04
Learning auxiliary categorical information for speech synthesis based on deep and recurrent neural networks 会议论文
, Tianjin, China, 17-20 Oct. 2016
Authors:  Zhengqi Wen;  Kehuang Li;  Zhen Huang;  Jianhua Tao;  Chin-Hui Lee
View  |  Adobe PDF(575Kb)  |  Favorite  |  View/Download:78/8  |  Submit date:2018/01/04
A Novel Research to Artificial Bandwidth Extension Based on Deep BLSTM Recurrent Neural Networks and Exemplar-based Sparse Representation 会议论文
, San Francisco,USA, Sept.8-12,2016
Authors:  Bin Liu;  Jianhua Tao
View  |  Adobe PDF(221Kb)  |  Favorite  |  View/Download:89/12  |  Submit date:2018/01/04
Emotional head motion predicting from prosodic and linguistic features 期刊论文
MULTIMEDIA TOOLS AND APPLICATIONS, 2016, 卷号: 75, 期号: 9, 页码: 5125-5146
Authors:  Yang, Minghao;  Jiang, Jinlin;  Tao, Jianhua;  Mu, Kaihui;  Li, Hao
View  |  Adobe PDF(1730Kb)  |  Favorite  |  View/Download:125/22  |  Submit date:2016/10/20
Visual Prosody  Head Gesture  Prosody Clustering  
Speech Enhancement Based on Analysis-Synthesis Framework with Improved Parameter Domain Enhancement 期刊论文
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2016, 卷号: 82, 期号: 2, 页码: 141-150
Authors:  Liu, Bin;  Tao, Jianhua;  Wen, Zhengqi;  Mo, Fuyuan;  Bin Liu
View  |  Adobe PDF(695Kb)  |  Favorite  |  View/Download:97/19  |  Submit date:2016/06/14
Analysis-synthesis Framework  Multi-band Summary Correlogram  Denoising Autoencoder  Speech Enhancement  Speech Coding  
Deep neural network based voice conversion with a large synthesized parallel corpus 会议论文
, Jeju, South Korea, 13-16 Dec. 2016
Authors:  Wen ZQ(温正棋);  Kehuang Li;  Jianhua Tao;  Chin-Hui Lee
View  |  Adobe PDF(384Kb)  |  Favorite  |  View/Download:42/7  |  Submit date:2018/01/04