Paper Info
Title
Subband-Based Blind Signal Processing for Source Separation in Convolutive Mixtures of Speech
Abstract
This paper describes a highly practical blind signal separation (BSS) scheme operating on subband domain data to blindly segregate convolutive mixtures of speech. The proposed method relies on spatiotemporal separation carried out in the time domain by using a multichannel blind deconvolution (MBD) algorithm that enforces separation by entropy maximization through the popular natural gradient algorithm (NGA). Numerical experiments with binaural impulse responses affirm the validity and illustrate the practical appeal of the presented technique even for difficult speech separation setups.
Year
DOI
Venue
2007
10.1109/ICASSP.2007.367220
ICASSP (4)
Keywords
Field
DocType
speech processing,convolutive speech mixtures,subband filtering,spatiotemporal separation,binaural impulse responses,subband-based blind signal processing,source separation,entropy maximization,natural gradient algorithm,time-domain analysis,blind signal separation,blind source separation,maximum entropy methods,transient response,multichannel blind deconvolution,mimo,deconvolution,finite impulse response filter,impulse response,blind deconvolution,time domain,signal processing
Time domain,Speech processing,Pattern recognition,Blind deconvolution,Computer science,Entropy maximization,Speech recognition,Impulse (physics),Artificial intelligence,Binaural recording,Blind signal separation,Source separation
Conference
Volume
ISSN
ISBN
4
1520-6149 E-ISBN : 1-4244-0728-1
1-4244-0728-1
Citations 
PageRank 
References 
7
0.61
10
Authors
2
Name
Order
Citations
PageRank
Kostas Kokkinakis1676.63
Philipos C. Loizou299171.00