Shift-invariant, multi-category phoneme recognition using Kohonen´s LVQ2

Author

McDermott, Erik ; Katagiri, Shigeru

Author_Institution

ATR Auditory & Visual Perception Res. Lab., Osaka, Japan

fYear

1989

fDate

23-26 May 1989

Firstpage

81

Abstract

The authors describe a shift-tolerant neural network architecture for phoneme recognition. The system is based on LVQ2, an algorithm which pays close attention to approximating the optimal Bayes decision line in a discrimination task. Recognition performances in the 98-99% correct range were obtained for LVQ2 networks aimed at speaker-dependent recognition of phonemes in small but ambiguous Japanese phonemic classes. A correct recognition rate of 97.7% was achieved by a single, larger LVQ2 network covering all Japanese consonants. These recognition results are at least as high as those obtained in the time delay neural network system and suggest that LVQ2 could be the basis for a successful speech recognition system

Keywords

neural nets; speech recognition; Japanese consonants; Kohonen´s LVQ2; learning vector quantisation; optimal Bayes decision line; phoneme recognition; shift-tolerant neural network; speech recognition; Delay effects; Laboratories; Machine learning; Neural networks; Poles and towers; Speech recognition; Vector quantization; Visual perception; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on

Conference_Location

Glasgow

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1989.266368

Filename

266368