Number of the records: 1

Adaptive Time-Domain Blind Separation of Speech Signals

SYSNO ASEP	0348108
Document Type	C - Proceedings Paper (int. conf.)
R&D Document Type	Conference Paper
Title	Adaptive Time-Domain Blind Separation of Speech Signals
Author(s)	Málek, J. (CZ) Koldovský, Zbyněk (UTIA-B)_RID Tichavský, Petr (UTIA-B)_{RID, ORCID}
Source Title	Lecture Notes in Computer Science, 6365. - Heidelberg : Springer-Verlag, 2010 / Gavrilova M.L. ; Kumar V. ; Mun Y. ; Tan C.J.K. ; Gervasi O. - ISBN 978-3-642-15994-7
Pages	s. 9-16
Number of pages	8 s.
Publication form	memory stick - memory stick
Action	Latent Variable Analysis and Signal Separation
Event date	27.09.2010-30.09.2010
VEvent location	St. Malo
Country	FR - France
Event type	WRD
Language	eng - English
Country	DE - Germany
Keywords	blind source separation ; speech ; convolutive mixture ; adaptive algorithms
Subject RIV	BB - Applied Statistics, Operational Research
R&D Projects	1M0572 GA MŠMT - Ministry of Education, Youth and Sports (MEYS)
	GA102/09/1278 GA ČR - Czech Science Foundation (CSF)
CEZ	AV0Z10750506 - UTIA-B (2005-2011)
Annotation	We present an adaptive algorithm for blind audio source separation (BASS) of moving sources via Independent Component Analysis (ICA) in time-domain. The method is shown to achieve good separation quality even with a short demixing filter length (L = 30). Our experiments show that the proposed adaptive algorithm can outperform the off-line version of the method (in terms of the average output SIR), even in the case in which the sources do not move, because it is capable of better adaptation to the nonstationarity of the speech.
Workplace	Institute of Information Theory and Automation
Contact	Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201.
Year of Publishing	2011

Number of the records: 1