Blind speech separation algorithm for dynamically mixing systems

Author

Leung, Chi-Tat ; Siu, Wan-chi

Author_Institution

Center for Multimedia Signal Process., Hong Kong Polytech. Univ., Hung Hom, China

fYear

2001

fDate

2001

Firstpage

222

Lastpage

223

Abstract

This paper presents a blind speech separation algorithm that is capable of extracting a speech signal from background noise or music based on a microphone-array. A variable rearrangement is derived to convert convolution operations into a simple matrix multiplication in dynamically mixing systems. The fast fixed-point algorithm is then extended to separate a speech signal from background noise in a realistic room with acoustic reverberation

Keywords

acoustic noise; architectural acoustics; array signal processing; convolution; matrix multiplication; microphones; music; speech enhancement; acoustic reverberation; background noise; blind speech separation algorithm; convolution operations; dynamically mixed systems; fast fixed-point algorithm; matrix multiplication; microphone-array; music; realistic room; speech signal; variable rearrangement; Background noise; Convolution; MIMO; Matrix converters; Multiple signal classification; Signal processing; Signal processing algorithms; Speech enhancement; Speech processing; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Consumer Electronics, 2001. ICCE. International Conference on

Conference_Location

Los Angeles, CA

Print_ISBN

0-7803-6622-0

Type

conf

DOI

10.1109/ICCE.2001.935284

Filename

935284