CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
Cross-domain cooperative deep stacking network for speech separation
Wei Jiang1; Shan Liang1; Like Dong2; Hong Yang2; Wenju Liu1; Yunji Wang3
Conference NameIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Source PublicationEI
Conference DateApril 19-24, 2015
Conference PlaceBrisbane, Australia
AbstractNowadays supervised speech separation has drawn much attention and shown great promise in the meantime. While there has been a lot of success, existing algorithms perform the task only in one preselected representative domain. In this study, we propose to perform the task in two different time-frequency domains simultaneously and cooperatively, which can model the implicit correlations between different representations of the same speech separation task. Besides, many time-frequency (T-F) units are dominated by noise in low signal-to-noise ratio (SNR) conditions, so more robust features are obtained by stacking features of original mixtures with that extracted from separated speech of each deep stacking network (DSN) block, which can be regarded as a denoisedversionoftheoriginalfeatures. Quantitativeexperiments show that the proposed cross-domain cooperative deep stacking network (DSN-CDC) has enhanced modeling capability as well as generalization ability, which outperforms a previous algorithm based on standard deep neural networks.
KeywordSpeech Separation Cross-domain Cooperative Structure Deep Stacking Network Deep Neural Network
Document Type会议论文
Corresponding AuthorWenju Liu
Affiliation1.NLPR, Institute of Automation, Chinese Academy of Sciences
2.Electric Power Research Institute of ShanXi Electric Power Company, China State Grid Corp
3.Electrical and Computer Engineering Department, The University of Texas at San Antonio, USA
Recommended Citation
GB/T 7714
Wei Jiang,Shan Liang,Like Dong,et al. Cross-domain cooperative deep stacking network for speech separation[C],2015.
Files in This Item: Download All
File Name/Size DocType Version Access License
WeiJiang2015.pdf(118KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wei Jiang]'s Articles
[Shan Liang]'s Articles
[Like Dong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wei Jiang]'s Articles
[Shan Liang]'s Articles
[Like Dong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wei Jiang]'s Articles
[Shan Liang]'s Articles
[Like Dong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: WeiJiang2015.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.