论文信息 - Tone recognition of isolated Cantonese syllables

Tone recognition of isolated Cantonese syllables

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. >

Pak-Chung Ching | Brian Kan-Wing Mak | Tan Lee | Lai-Wan Chan | Y. H. Cheng

[1] Hsiao-Chuan Wang,et al. Hidden Markov model for Mandarin lexical tone recognition , 1988, IEEE Trans. Acoust. Speech Signal Process..

[2] P. C. Ching,et al. Discrete word recognition using energy-time profiles , 1987 .

[3] Akira Ichikawa,et al. Phoneme recognition in continuous speech , 1982, ICASSP.

[4] M. Sondhi,et al. New methods of pitch extraction , 1968 .

[5] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[6] Yuen-Yuen Fok Chan. A perceptual study of tones in Cantonese , 1974 .

[7] Kenneth L. Pike,et al. Tone languages : a technique for determining the number and type of pitch contrasts in a language, with studies in tonemic substitution and fusion , 1950 .

[8] Oi-Kan Yue Hashimoto,et al. Studies in the Yue dialects I: Phonology of Cantonese , 1973 .

[9] Hsiao-Chuan Wang,et al. Tone recognition of polysyllabic words in Mandarin speech , 1989 .