A real-time Chinese speech recognition system with unlimited vocabulary

Author

Gao, Yuqing ; Huang, Taiyi ; Lin, Zhiwei ; Xu, Bo ; Xu, Dongxin

Author_Institution

Inst. of Autom., Chinese Acad. of Sci., Beijing, China

fYear

1991

fDate

14-17 Apr 1991

Firstpage

257

Abstract

A Chinese speech recognizer with unlimited vocabulary is described. The system has two major components: the acoustic recognition component, which includes an HMM (hidden Markov model)-based phone recognizer, a NN (neural network)-based initial refiner, and a NN-based tone classifier; and the lexical and homonym processor, which is based on a knowledge database extracted from large amounts of texts. This real-time recognizer is implemented on a PC-386 enhanced by only one digital signal processing board on which a TMS-320c25 chip operates as the CPU. On average, it takes only 0.19 s to recognize a one-syllable word. The recognition accuracy for syllables, tones, and words is 92.5%, 99.6%, and 97.5%, respectively

Keywords

Markov processes; neural nets; real-time systems; speech recognition; Chinese; HMM; PC-386; TMS-320c25 chip; acoustic recognition component; digital signal processing board; hidden Markov model; homonym processor; initial refiner; knowledge database; lexical processor; neural network; phone recognizer; real-time recognizer; speech recognition; syllable recognition; tone classifier; tone recognition; unlimited vocabulary; word recognition; Automatic speech recognition; Hidden Markov models; Laboratories; Natural languages; Pattern recognition; Real time systems; Speech processing; Speech recognition; Text recognition; Vocabulary;

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.1991.150326

Filename

150326