Tone recognition of isolated Cantonese syllables

Author

Lee, Tan ; Ching, P.C. ; Chan, L.W. ; Cheng, Y.H. ; Mak, Brian

Author_Institution

Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, Hong Kong

Volume

3

Issue

3

fYear

1995

fDate

5/1/1995 12:00:00 AM

Firstpage

204

Lastpage

209

Abstract

Tone identification is essential for the recognition of the Chinese language, specifically far Cantonese which is well known for being very rich in tones. The paper presents an efficient method for tone recognition of isolated Cantonese syllables. Suprasegmental feature parameters are extracted from the voiced portion of a monosyllabic utterance and a three-layer feedforward neural network is used to classify these feature vectors. Using a phonologically complete vocabulary of 234 distinct syllables, the recognition accuracy for single-speaker and multispeaker is given by 89.0% and 87.6% respectively

Keywords

feature extraction; feedforward neural nets; multilayer perceptrons; natural languages; speech recognition; Chinese language; feature vectors; isolated Cantonese syllables; monosyllabic utterance; multispeaker; phonologically complete vocabulary; single-speaker; suprasegmental feature parameters; three-layer feedforward neural network; tone identification; tone recognition; voiced portion; Backpropagation algorithms; Computer science; Feature extraction; Feedforward neural networks; Multi-layer neural network; Natural languages; Neural networks; Neurons; Speech recognition; Vocabulary;

fLanguage

English

Journal_Title

Speech and Audio Processing, IEEE Transactions on

Publisher

ieee

ISSN

1063-6676

Type

jour

DOI

10.1109/89.388147

Filename

388147