Title :
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
fDate :
5/1/1995 12:00:00 AM
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;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on
