Robust speech parameters extraction for word recognition in noise using neural networks

Author

Barbier, Laurent ; Chollet, Gérard

Author_Institution

Telecom Paris, CNRS, France

fYear

1991

fDate

14-17 Apr 1991

Firstpage

145

Abstract

An attempt was made to enhance the performance of a DTW (dynamic time warping) speech recognizer by preprocessing speech parameters using a neural network transformation. A multilayer perceptron trained with speech utterances of a single speaker has been used in front of a DTW recognizer. Results show an improvement of about 15% in the recognition rate in all cases, even with a speaker that was not used for training. If the network is not completely speaker independent, a dynamic adaptation to the speaker could be performed

Keywords

neural nets; noise; speech analysis and processing; speech recognition; dynamic adaptation; dynamic time warping; multilayer perceptron; neural networks; noise; recognition rate; speech parameters extraction; speech parameters preprocessing; speech recognizer; speech utterances; word recognition; Frequency; Intelligent networks; Low-frequency noise; Neural networks; Noise robustness; Parameter extraction; Signal to noise ratio; Speech enhancement; Speech recognition; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on

Conference_Location

Toronto, Ont.

ISSN

1520-6149

Print_ISBN

0-7803-0003-3

Type

conf

DOI

10.1109/ICASSP.1991.150298

Filename

150298