Speaker-independent phoneme recognition using large-scale neural networks

Author

Nakamura, Satoru ; Sawai, Hidefumi ; Sugiyama, Masahide

Author_Institution

Fac. of Sci. & Technol., Keio Univ., Yokohama, Japan

Volume

1

fYear

1992

fDate

23-26 Mar 1992

Firstpage

409

Abstract

The authors describe a large-scale neural network architecture based on TDNN (time-delay neural networks) for speaker-independent phoneme recognition which represents an advance over speaker-dependent and multi-speaker phoneme recognition. Based on a preliminary study on speaker-independent phoneme recognition for voiced stops |b,d,g|, a large-scale network is constructed with about 330000 connections in a modular fashion. For speaker-independent all-consonant recognition, a multi-speaker training approach is implemented with several devices in the process of training. This network finally achieved favorable results for speaker-independent phoneme recognition

Keywords

neural nets; speech recognition; TDNN; large-scale neural network architecture; modular network; multi-speaker training; speaker-independent all-consonant recognition; speaker-independent phoneme recognition; time-delay neural networks; voiced stops; Laboratories; Large-scale systems; Neural networks; Research and development; Speech recognition; Telephony; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on

Conference_Location

San Francisco, CA

ISSN

1520-6149

Print_ISBN

0-7803-0532-9

Type

conf

DOI

10.1109/ICASSP.1992.225885

Filename

225885