DocumentCode :
885008
Title :
Improving Isolation of Blindly Separated Sources Using Time-Frequency Masking
Author :
Cobos, Maximo ; Lopez, Jose J.
Author_Institution :
Inst. for Telecommun. & Multimedia Applic., Tech. Univ. of Valencia, Valencia
Volume :
15
fYear :
2008
fDate :
6/30/1905 12:00:00 AM
Firstpage :
617
Lastpage :
620
Abstract :
A refinement technique based on time-frequency masking is proposed to improve source isolation in blind audio source separation algorithms. The refinement technique uses an energy-normalized source-to-interference ratio in order to identify and eliminate interfering energy from the extracted sources. Some examples using this refinement method with different separation algorithms are discussed. The results show that source isolation can be significantly enhanced with negligible degradation of the separated sources.
Keywords :
audio signal processing; blind source separation; blind audio source separation algorithms; energy-normalized source-to-interference ratio; source isolation; time-frequency masking; Associate members; Degradation; Image sensors; Independent component analysis; Mathematical model; Multiple signal classification; Signal processing; Signal processing algorithms; Source separation; Time frequency analysis; Audio source separation; time-frequency masking;
fLanguage :
English
Journal_Title :
Signal Processing Letters, IEEE
Publisher :
ieee
ISSN :
1070-9908
Type :
jour
DOI :
10.1109/LSP.2008.2002927
Filename :
4639582
Link To Document :
بازگشت