A hierarchical LPNN network for noise reduction and noise degraded speech recognition

Author

Gao, Yuqing ; Haton, Jean Paul

Author_Institution

Apple-ISS Res. Center, Inst. of Syst. Sci., Singapore

Volume

ii

fYear

1994

fDate

19-22 Apr 1994

Abstract

We present a new linked predictive neural network structure-hierarchical LPNN-and the speech recognition system based on it. This neural network is specially developed for the noise degraded speech recognition problem and integrates the speech recognition and noise reduction in a unified structure. The network is trained according to joint optimization criterion both for the signal prediction and for the noise reduction. We present results which indicate that joint optimization results in a better speech recognition performance of the all over system for noise degraded speech signals

Keywords

learning (artificial intelligence); neural nets; noise; optimisation; prediction theory; speech enhancement; speech recognition; hierarchical LPNN network; joint optimization; linked predictive neural network; noise degraded speech recognition; noise degraded speech signal; noise reduction; signal prediction; speech enhancement; speech recognition performance; speech recognition system; Data preprocessing; Degradation; Multilayer perceptrons; Neural networks; Noise reduction; Speech enhancement; Speech recognition; System testing; Training data; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on

Conference_Location

Adelaide, SA

ISSN

1520-6149

Print_ISBN

0-7803-1775-0

Type

conf

DOI

10.1109/ICASSP.1994.389711

Filename

389711