A large vocabulary word recognition system based on syllable recognition and nonlinear word matching

Author

Matsu´ura, Hiroshi ; Nitta, Tsuneo ; Hirai, Shoichi ; Takebayashi, Yoichi ; Tsuboi, Hiroyuki ; Kanazawa, Hiroshi

Author_Institution

Toshiba Corp., Kawasaki City, Japan

fYear

1988

fDate

11-14 Apr 1988

Firstpage

183

Abstract

A practical Japanese large-vocabulary recognition system that is speaker-adaptive has been developed. The system has to notable features. The first is low-cost hardware which can realise the precise syllable recognition and the high speed speaker-adaptation using the Karhunen-Loeve expansion. The second is nonlinear word matching which deals with syllable addition and deletion, and reduces the restriction on acceptable utterances. The system has been applied to data entry systems such as train-station-names, family-names, and given-names input and also to a map data search task in which place names were verified. Recognition experiments have been carried out on a 2000-word vocabulary. The word-recognition rate was 93.7% for 1000 utterances by five male speakers

Keywords

speech recognition; Japanese; Karhunen-Loeve expansion; acceptable utterances; data entry systems; family-names; large vocabulary word recognition system; male speakers; map data search task; nonlinear word matching; place names; speech recognition; syllable addition; syllable recognition; train-station-names; Band pass filters; Character recognition; Covariance matrix; Hardware; Optical character recognition software; Optical noise; Pattern recognition; Research and development; Speech recognition; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on

Conference_Location

New York, NY

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1988.196543

Filename

196543