CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
Two-Stage Multi-Target Joint Learning for Monaural Speech Separation
Shuai, Nie1; Shan, Liang1; Wei, Xue1; XueLiang, Zhang2; WenJu, Liu1; Like Dong3; Hong Yang3
2015
Conference NameAnnual Conference of the International Speech Communication Association (INTERSPEECH)
Source PublicationAnnual Conference of the International Speech Communication Association (INTERSPEECH)
Pages1503-1507
Conference Date2015
Conference PlaceDresden Germany
AbstractRecently, supervised speech separation has been extensively
studied and shown considerable promise. Due to the temporal
continuity of speech, speech auditory features and separation
targets present prominent spectro-temporal structures
and strong correlations over the time-frequency (T-F) domain,
which can be exploited for speech separation. However, many
supervised speech separation methods independently model
each T-F unit with only one target and much ignore these useful
information. In this paper, we propose a two-stage multi-target
joint learning method to jointly model the related speech separation
targets at the frame level. Systematic experiments show
that the proposed approach consistently achieves better separation
and generalization performances in the low signal-to-noise
ratio(SNR) conditions.
KeywordSpeech Separation Multi-target Learning Computational Auditory Scene Analysis (Casa)
Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/11024
Collection模式识别国家重点实验室_机器人视觉
Affiliation1.National Laboratory of Patten Recognition, Institute of Automation, Chinese Academy of Sciences
2.College of Computer Science, Inner Mongolia University
3.Electric Power Research Institute of ShanXi Electric Power Company, China State Grid Corp
Recommended Citation
GB/T 7714
Shuai, Nie,Shan, Liang,Wei, Xue,et al. Two-Stage Multi-Target Joint Learning for Monaural Speech Separation[C],2015:1503-1507.
Files in This Item: Download All
File Name/Size DocType Version Access License
ShuaiNie2015.pdf(185KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Shuai, Nie]'s Articles
[Shan, Liang]'s Articles
[Wei, Xue]'s Articles
Baidu academic
Similar articles in Baidu academic
[Shuai, Nie]'s Articles
[Shan, Liang]'s Articles
[Wei, Xue]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shuai, Nie]'s Articles
[Shan, Liang]'s Articles
[Wei, Xue]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: ShuaiNie2015.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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