QQ客服 官方微博 反馈留言

浏览/检索结果: 共9条，第1-9条 帮助 限定条件 发表日期：2018    专题：自动化研究所    第一署名单位    第一作者单位    通讯作者单位     已选(0)清除 条数/页：5101520253035404550556065707580859095100   排序方式：请选择作者升序作者降序题名升序题名降序发表日期升序发表日期降序提交时间升序提交时间降序 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 作者:  Yi, Jiangyan;  Wen, Zhengqi;  Tao, Jianhua;  Ni, Hao;  Liu, Bin 收藏  |  浏览/下载：23/0  |  提交时间：2018/01/04 Multi-accent  Mandarin Speech Recognition  Lstm-rnn-ctc  Model Adaptation  Ctc Regularization   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 作者:  Zheng, Yibin;  Li, Ya;  Wen, Zhengqi;  Liu, Bin;  Tao, Jianhua 收藏  |  浏览/下载：20/0  |  提交时间：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 作者:  Wen, Zhengqi;  Li, Kehuang;  Huang, Zhen;  Lee, Chin-Hui;  Tao, Jianhua 收藏  |  浏览/下载：18/0  |  提交时间：2018/01/05 Dnn-based Speech Synthesis  Vocoder  Speech Parametrization  Blstm  Phoneme Embedded Vector  Multi-task Learning  Pitch-scaled Spectrum   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 作者:  Zheng, Yibin;  Li, Ya;  Wen, Zhengqi;  Liu, Bin;  Tao, Jianhua 收藏  |  浏览/下载：9/0  |  提交时间：2020/10/27 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 作者:  Wen, Zhengqi;  Li, Kehuang;  Huang, Zhen;  Lee, Chin-Hui;  Tao, Jianhua 收藏  |  浏览/下载：4/0  |  提交时间：2020/10/27 Dnn-based Speech Synthesis  Vocoder  Speech Parametrization  Blstm  Phoneme Embedded Vector  Multi-task Learning  Pitch-scaled Spectrum   Stabilization of atmospheric turbulence-distorted video containing moving objects using the monogenic signal 期刊论文 SIGNAL PROCESSING-IMAGE COMMUNICATION, 2018, 卷号: 63, 页码: 19-29 作者:  Zhang, Chao;  Zhou, Fugen;  Xue, Bindang;  Xue, Wenfang 收藏  |  浏览/下载：36/0  |  提交时间：2018/10/10 Atmospheric Turbulence  Video Stabilization  Monogenic Signal   Self-Paced AutoEncoder 期刊论文 IEEE SIGNAL PROCESSING LETTERS, 2018, 卷号: 25, 期号: 7, 页码: 1054-1058 作者:  Tingzhao Yu;  Chaoxu Guo;  Lingfeng Wang;  Shiming Xiang;  Chunhong Pan 收藏  |  浏览/下载：35/0  |  提交时间：2019/05/06 Autoencoder (Ae)  Self-paced Learning (Spl)  Temporal Encoding (Te)  Video Analysis   End-to-End Continuous Emotion Recognition from Video Using 3D Convlstm Networks 会议论文 Canada, 2018 作者:  Huang, Jian;  Li, Ya;  Tao, Jianhua;  Lian, Zheng;  Yi, Jiangyan 收藏  |  浏览/下载：26/0  |  提交时间：2018/11/26 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 作者:  Jiangyan Yi;  Zhengqi Wen;  Jianhua Tao;  Hao Ni;  Bin Liu 收藏  |  浏览/下载：8/0  |  提交时间：2020/10/22 multi-accent, Mandarin speech recognition,LSTM-RNN-CTC, model adaptation, CTC regularization