Přístupnostní navigace
E-application
Search Search Close
Publication detail
SMÉKAL, Z. ČERMÁK, J.
Original Title
Undertermined Blind Source Separation Using Linear Separation System
Type
journal article - other
Language
English
Original Abstract
In automatic speech recognition and speech modal analysis, good quality of input speech signal is often required. The hit rate of recognizers is lowered by degradation of speech quality due to the noise. Blind source separation can be used to enhance the speech signal as a part of preprocessing techniques. This paper presents a multi channel linear blind source separation method that can be applied even in underdetermined case (UDC) i.e. when the number of source signals is higher than the number of sensors. The experiments show that our system outperforms conventional time-frequency binary masking (TFBM) in both determined and underdetermined cases.
Keywords
Array signal processing, beamforming, blind source separation, speech processing, time-frequency binary masking.
Authors
SMÉKAL, Z.; ČERMÁK, J.
RIV year
2009
Released
6. 3. 2009
Publisher
Springer Verlag
Location
Berlin
ISBN
0302-9743
Periodical
Lecture Notes in Computer Science
Year of study
Number
5398
State
Federal Republic of Germany
Pages from
300
Pages to
305
Pages count
5
BibTex
@article{BUT47335, author="Zdeněk {Smékal} and Jan {Čermák}", title="Undertermined Blind Source Separation Using Linear Separation System", journal="Lecture Notes in Computer Science", year="2009", volume="2009", number="5398", pages="300--305", issn="0302-9743" }