Speech separation by simulating the cocktail party effect with a neural network controlled Wiener filter

Author

Cao, Yuchang ; Sridharan, Sridha ; Moody, Miles

Author_Institution

Sch. of Electr. & Electron. Syst. Eng., Queensland Univ. of Technol., Brisbane, Qld., Australia

Volume

4

fYear

1997

fDate

21-24 Apr 1997

Firstpage

3261

Abstract

A novel speech separation structure which simulates the cocktail party effect using a modified iterative Wiener filter and a multi-layer perceptron neural network is presented. The neural network is used as a speaker recognition system to control the iterative Wiener filter. The neural network is a modified perceptron with a hidden layer using feature data extracted from LPC cepstral analysis. The proposed technique has been successfully used for speech separation when the interference is competing speech or broad band noise

Keywords

Wiener filters; cepstral analysis; digital simulation; feature extraction; filtering theory; iterative methods; linear predictive coding; multilayer perceptrons; simulation; speaker recognition; speech enhancement; speech processing; LPC cepstral analysis; broadband noise; cocktail party effect simulation; feature data extraction; hidden layer; modified iterative Wiener filter; multilayer perceptron neural network; neural network controlled Wiener filter; speaker recognition system; speech enhancement; speech interference; speech separation; Control systems; Data mining; Feature extraction; Linear predictive coding; Multi-layer neural network; Multilayer perceptrons; Neural networks; Speaker recognition; Speech enhancement; Wiener filter;

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.1997.595489

Filename

595489