A connectionist model for speaker-independent isolated word recognition

Author

Zhu, Ming ; Fellbaum, K.

Author_Institution

Inst. of Telecommun., Tech. Univ. of Berlin, West Germany

fYear

1990

fDate

3-6 Apr 1990

Firstpage

529

Abstract

A connectionist model for speaker-independent isolated word recognition is presented. It consists of an efficient preprocessor and a network of multilayer perceptrons. The preprocessor measures the local spectral similarities by implementing a multicodebook vector quantizer and compresses nonlinearly each speech pattern into a fixed length of 24 triples. The network makes the final decision by decoding these triples which contain temporal information and minimum distortions. Preliminary experiments show a recognition rate of 95.5%, which indicates that a properly designed combination of a preprocessing scheme and a neural network can greatly reduce the computational load as well as increase recognition rates

Keywords

decoding; neural nets; spectral analysis; speech recognition; connectionist model; decoding; multicodebook vector quantizer; multilayer perceptrons; neural nets; speaker-independent isolated word recognition; speech recognition; Computer networks; Costs; Decoding; Distortion measurement; Feature extraction; Length measurement; Multi-layer neural network; Multilayer perceptrons; Neural networks; Speech; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.115766

Filename

115766