CASIA OpenIR

Browse/Search Results:  1-10 of 17 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
FOCAL LOSS AND DOUBLE-EDGE-TRIGGERED DETECTOR FOR ROBUST SMALL-FOOTPRINT KEYWORD SPOTTING 会议论文
, Brighton, United Kingdom, 2019-5-13
Authors:  Bin,Liu;  Shuai,Nie;  Yaping,Zhang;  Shan,Liang;  Zhanlei,Yang;  Wenju,Liu
View  |  Adobe PDF(1111Kb)  |  Favorite  |  View/Download:12/3  |  Submit date:2020/05/15
Keyword Spotting  Focal Loss  Double-edgetriggered Detecting Method  Speech Recognition  
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
Authors:  Shuai, Nie;  Shan, Liang;  Hao, Li;  XueLiang, Zhang;  ZhanLei, Yang;  WenJu, Liu;  LiKe, Dong
View  |  Adobe PDF(408Kb)  |  Favorite  |  View/Download:178/44  |  Submit date:2016/04/12
Speech Separation  Deep Neural Network  Nonnegative Matrix Factorization  Spectro-temporal Structures  
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
Authors:  Mingming Chen;  Zhanlei Yang;  Jizhong Liang;  Yanpeng Li;  Wenju Liu
View  |  Adobe PDF(406Kb)  |  Favorite  |  View/Download:100/34  |  Submit date:2018/01/04
Improving Deep Neural Networks Using Softplus Units 会议论文
IJCNN, Ireland, 2015
Authors:  Hao Zheng;  Zhanlei Yang;  Wenju Liu;  Jizhong Liang;  Yanpeng Li
View  |  Adobe PDF(232Kb)  |  Favorite  |  View/Download:287/157  |  Submit date:2016/06/28
Softplus  Dropout  Deep Neural Networks  Timit  
Attribute Knowledge Integration for Speech Recognition Based on Multi-task Learning Neural Networks 会议论文
INTERSPEECH, Dresden, Germany, 2015
Authors:  Hao Zheng;  Zhanlei Yang;  Liwei Qiao;  Jianping Li;  Wenju Liu
View  |  Adobe PDF(388Kb)  |  Favorite  |  View/Download:121/24  |  Submit date:2016/06/28
Multi-task Learning  Automatic Attribute Transcription  Deep Neural Networks  
Latent topic model for audio retrieval 期刊论文
PATTERN RECOGNITION, 2014, 卷号: 47, 期号: 3, 页码: 1138-1143
Authors:  Hu, Pengfei;  Liu, Wenju;  Jiang, Wei;  Yang, Zhanlei
Favorite  |  View/Download:97/0  |  Submit date:2015/08/12
Topic Model  Lda  Gaussian Distribution  Audio Retrieval  
Improving native accent identification using deep neural networks 会议论文
Annual Conference of the International Speech Communication Association (INTERSPEECH), 2014
Authors:  Chen, Mingming;  Yang, Zhanlei;  Zheng, Hao;  Liu, Wenju
Favorite  |  View/Download:59/0  |  Submit date:2015/08/19
Deep neural networks for Mandarin tone recognition 会议论文
International Joint Conference on Neural Networks (IJCNN), 2014
Authors:  Mingming Chen;  Zhanlei Yang;  Wenju Liu
Favorite  |  View/Download:70/0  |  Submit date:2015/08/19
Improving Deep Neural Networks by Using Sparse Dropout Strategy 会议论文
ChinaSIP, Xi an, Shanxi, China, 2014
Authors:  Zheng Hao;  Mingming Chen;  Wenju Liu;  Zhanlei Yang;  Shan Liang;  Hao Zheng
View  |  Adobe PDF(146Kb)  |  Favorite  |  View/Download:107/23  |  Submit date:2016/06/28
Dropout  Sparse Dropout  Deep Neural Networks  Deep Learning  
基于最大似然线性回归的随机段模型说话人自适应研究 期刊论文
计算机工程与科学, 2014, 卷号: 036, 期号: 008, 页码: 1604
Authors:  晁浩;  杨占磊;  刘文举
Favorite  |  View/Download:0/0  |  Submit date:2020/03/30