CASIA OpenIR

Browse/Search Results:  1-10 of 23 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
Bidirectional Adversarial Domain Adaptation with Semantic Consistency 会议论文
, 中国西安, 2019.11.08-2019.11.11
Authors:  Yaping Zhang;  Shuai Nie;  Shan Liang;  Wenju Liu
Adobe PDF(811Kb)  |  Favorite  |  View/Download:14/1  |  Submit date:2020/05/15
Jointly Adversarial Enhancement Training for Robust End-to-End Speech Recognition 会议论文
, Graz, Austria, 2019-9-15
Authors:  Bin,Liu;  Shuai,Nie;  Shan,Liang;  Wenju,Liu;  Meng,Yu;  Lianwu,Chen;  Shouye,Peng;  Changliang,Li
Adobe PDF(350Kb)  |  Favorite  |  View/Download:7/1  |  Submit date:2020/05/15
End-to-end Speech Recognition  Robust Speech Recognition  Speech Enhancement  Generative Adversarial Networks  
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
Adobe PDF(1111Kb)  |  Favorite  |  View/Download:15/4  |  Submit date:2020/05/15
Keyword Spotting  Focal Loss  Double-edgetriggered Detecting Method  Speech Recognition  
Robust offline handwritten character recognition through exploring writer-independent features under the guidance of printed data 期刊论文
PATTERN RECOGNITION LETTERS, 2018, 卷号: 106, 期号: 无, 页码: 20-26
Authors:  Zhang, Yaping;  Liang, Shan;  Nie, Shuai;  Liu, Wenju;  Peng, Shouye
Adobe PDF(756Kb)  |  Favorite  |  View/Download:77/2  |  Submit date:2018/10/10
Handwritten Character Recognition  Writer-independent Features  Adversarial Feature Learning  Convolutional Neural Network  
Boosting noise robustness of acoustic model via deep adversarial training 会议论文
, 加拿大卡尔加里, 2018-4-15
Authors:  Bin,Liu;  Shuai,Nie;  Yaping,Zhang;  Dengfeng,Ke;  Shan,Liang;  Wenju Liu
Adobe PDF(300Kb)  |  Favorite  |  View/Download:14/3  |  Submit date:2020/05/15
Robust Speech Recognition  Deep Adversarial Training  Acoustic Model  Generative Adversarial Net  
基于优化浮值掩蔽的监督性语音分离 期刊论文
自动化学报, 2018, 卷号: 44, 期号: 10, 页码: 1876
Authors:  夏莎莎;  张学良;  梁山
Favorite  |  View/Download:1/0  |  Submit date:2020/03/30
Long Short-term Memory Recurrent Neural Network based Segment Features for Music Genre Classification 会议论文
, Tianjin, China, 2016-10-17
Authors:  Dai J(戴佳);  Liang Shan;  Xue Wei;  Ni Chongjia;  Liu Wenju
Adobe PDF(334Kb)  |  Favorite  |  View/Download:184/76  |  Submit date:2017/06/07
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
Adobe PDF(408Kb)  |  Favorite  |  View/Download:182/45  |  Submit date:2016/04/12
Speech Separation  Deep Neural Network  Nonnegative Matrix Factorization  Spectro-temporal Structures  
Two-Stage Multi-Target Joint Learning for Monaural Speech Separation 会议论文
, Dresden, Germany, Sept. 6-10 2015
Authors:  Shuai Nie;  Shan Liang;  Wei Xue;  Xueliang Zhang;  Wenju Liu
Adobe PDF(193Kb)  |  Favorite  |  View/Download:83/12  |  Submit date:2018/01/04
Noise Robust Direction of Arrival Estimation for Speech Source With Weighted Bispectrum Spatial Correlation Matrix 期刊论文
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2015, 卷号: 9, 期号: 5, 页码: 837-851
Authors:  Xue, Wei;  Liu, Wenju;  Liang, Shan
Adobe PDF(3205Kb)  |  Favorite  |  View/Download:124/25  |  Submit date:2015/09/23
Direction Of Arrival (Doa) Estimation  Microphone Array Signal Processing  High Order Statistics  Bispectrum