CASIA OpenIR
(本次检索基于用户作品认领结果)

浏览/检索结果: 共18条,第1-10条 帮助

限定条件            
已选(0)清除 条数/页:   排序方式:
Exploiting the directional coherence function for multichannel source extraction 期刊论文
SPEECH COMMUNICATION, 2021, 卷号: 128, 页码: 1-14
作者:  Liang, Shan;  Li, Guanjun;  Nie, Shuai;  Yang, ZhanLei;  Liu, WenJu;  Tao, Jianhua
收藏  |  浏览/下载:220/0  |  提交时间:2021/05/06
Directional coherence function  Coherent-to-Diffuse Ratio  General sidelobe canceller  Desired Speech Presence Probability  
Exploiting Spectro-temporal Structures Using NMF For DNN-based Supervised Speech Separation 会议论文
, Shanghai, China, 2016-3-20~2016-3-25
作者:  Nie S(聂帅);  Shan Liang;  Hao Li;  XueLiang Zhang;  ZhanLei Yang;  WenJu Liu
Adobe PDF(357Kb)  |  收藏  |  浏览/下载:168/62  |  提交时间:2020/10/22
Stochastic Multiple Choice Learning for Acoustic Modeling 会议论文
, Rio de Janeiro, 巴西, 2018-07-08
作者:  Liu, Bin;  Nie, Shuai;  Liang, Shan;  Yang, Zhanlei;  Liu, Wenju
Adobe PDF(529Kb)  |  收藏  |  浏览/下载:194/70  |  提交时间:2020/06/08
Focal Loss And Double-Edge-Triggered Detector For Robust Small-Footprint Keyword Spotting 会议论文
, Brighton, United Kingdom, 2019-5-13
作者:  Liu, Bin;  Nie, Shuai;  Zhang, Yaping;  Liang, Shan;  Yang, Zhanlei;  Liu, Wenju
Adobe PDF(1111Kb)  |  收藏  |  浏览/下载:697/394  |  提交时间:2020/05/15
Keyword Spotting  Focal Loss  Double-edgetriggered Detecting Method  Speech Recognition  
Improving Deep Neural Networks Based Multi-Accent Mandarin Speech Recognition Using I-Vectors and Accent-Specific Top Layer 会议论文
, Dresden, Germany, Sept. 6-10 2015
作者:  Mingming Chen;  Zhanlei Yang;  Jizhong Liang;  Yanpeng Li;  Wenju Liu
浏览  |  Adobe PDF(406Kb)  |  收藏  |  浏览/下载:363/154  |  提交时间:2018/01/04
Attribute Knowledge Integration for Speech Recognition Based on Multi-task Learning Neural Networks 会议论文
INTERSPEECH, Dresden, Germany, 2015
作者:  Hao Zheng;  Zhanlei Yang;  Liwei Qiao;  Jianping Li;  Wenju Liu
浏览  |  Adobe PDF(388Kb)  |  收藏  |  浏览/下载:392/121  |  提交时间:2016/06/28
Multi-task Learning  Automatic Attribute Transcription  Deep Neural Networks  
Improving Deep Neural Networks Using Softplus Units 会议论文
IJCNN, Ireland, 2015
作者:  Hao Zheng;  Zhanlei Yang;  Wenju Liu;  Jizhong Liang;  Yanpeng Li
浏览  |  Adobe PDF(232Kb)  |  收藏  |  浏览/下载:758/355  |  提交时间:2016/06/28
Softplus  Dropout  Deep Neural Networks  Timit  
Improving Deep Neural Networks by Using Sparse Dropout Strategy 会议论文
ChinaSIP, Xi an, Shanxi, China, 2014
作者:  Zheng Hao;  Mingming Chen;  Wenju Liu;  Zhanlei Yang;  Shan Liang;  Hao Zheng
浏览  |  Adobe PDF(146Kb)  |  收藏  |  浏览/下载:291/93  |  提交时间:2016/06/28
Dropout  Sparse Dropout  Deep Neural Networks  Deep Learning  
EXPLOITING SPECTRO-TEMPORAL STRUCTURES USING NMF FOR DNN-BASED SUPERVISED SPEECH SEPARATION 会议论文
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shang Hai, China, 2016
作者:  Shuai, Nie;  Shan, Liang;  Hao, Li;  XueLiang, Zhang;  ZhanLei, Yang;  WenJu, Liu;  LiKe, Dong
浏览  |  Adobe PDF(408Kb)  |  收藏  |  浏览/下载:491/133  |  提交时间:2016/04/12
Speech Separation  Deep Neural Network  Nonnegative Matrix Factorization  Spectro-temporal Structures  
一种发音稳定段辅助的语音识别优化解码方法及装置 专利
专利类型: 发明, 专利号: CN201210514763.9, 申请日期: 2012-12-04, 公开日期: 2013-04-03
发明人:  刘文举;  杨占磊
收藏  |  浏览/下载:133/0  |  提交时间:2015/09/22