Paper Info
Title
A robust approach to reverberant blind source separation in the presence of noise for arbitrarily arranged sensors
Abstract
Considerable attention has been devoted to the reverberant blind source separation problem: in particular, the concept of time-frequency masking. However, realistic acoustic scenarios often comprise not only reverberation, but also additive noise due to factors such as non-ideal channels. This paper presents robust evaluations of a time-frequency masking approach for separation in such realistic conditions. The fuzzy c-means clustering algorithm is used to cluster spatial feature cues into a time-frequency mask. Experimental results demonstrated superiority in separation, with notable improvements in the SNR additionally observed. Not only does this establish the proposed scheme viable for reverberant blind source separation, but also as a credible means of speech enhancement in the presence of additive broadband noise.
Year
DOI
Venue
2012
10.1109/ICASSP.2012.6288402
Acoustics, Speech and Signal Processing
Keywords
Field
DocType
blind source separation,fuzzy set theory,pattern clustering,sensors,speech enhancement,time-frequency analysis,SNR,additive broadband noise,arbitrarily arranged sensors,fuzzy c-means clustering algorithm,non-ideal channels,realistic acoustic scenarios,reverberant blind source separation problem,robust evaluations,spatial feature,speech enhancement,time-frequency masking approach,Blind source separation,additive noise,fuzzy c-means clustering,reverberation,time-frequency mask estimation
Speech enhancement,Masking (art),Computer science,Artificial intelligence,Cluster analysis,Blind signal separation,Reverberation,Pattern recognition,Signal-to-noise ratio,Communication channel,Speech recognition,Time–frequency analysis,Acoustics
Conference
ISSN
ISBN
Citations 
1520-6149 E-ISBN : 978-1-4673-0044-5
978-1-4673-0044-5
0
PageRank 
References 
Authors
0.34
8
3
Name
Order
Citations
PageRank
Ingrid Jafari171.86
Roberto Togneri281448.33
Sven Nordholm340562.82