Blind separation and restoration of signals mixed in convolutive environment

Author

Xi, Jiangtao ; Reilly, James P.

Author_Institution

Commun. Res. Lab., McMaster Univ., Hamilton, Ont., Canada

Volume

2

fYear

1997

fDate

21-24 Apr 1997

Firstpage

1327

Abstract

This paper proposes new neural network approaches for separating and restoring signals mixed through FIR channels. Firstly, a set of maximal entropy based training rules are developed. Secondly, a new scheme for restoring the original signals is proposed for the 2×2 case. Computer simulation results for speech signals are presented to verify the proposed approaches

Keywords

FIR filters; convolution; filtering theory; learning (artificial intelligence); maximum entropy methods; neural nets; signal restoration; speech processing; telecommunication channels; FIR channels; FIR filters; blind signal restoration; blind signal separation; computer simulation results; convolutive environment; maximal entropy based training rules; neural network; signal restoration; speech signals; Blind source separation; Computer simulation; Delay effects; Entropy; Finite impulse response filter; Intelligent networks; Neural networks; Signal processing algorithms; Signal restoration; Speech;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on

Conference_Location

Munich

ISSN

1520-6149

Print_ISBN

0-8186-7919-0

Type

conf

DOI

10.1109/ICASSP.1997.596191

Filename

596191