论文信息 - From phonology and acoustic properties to automatic recognition of Cantonese

From phonology and acoustic properties to automatic recognition of Cantonese

Cantonese is a common Chinese dialect used by tens of millions of people residing in Southern China and in Hong Kong. It is a monosyllabic and tonal language and is very different from the Chinese official language, Putonghua or Mandarin. We describe the recent development in designing efficient algorithms based on artificial neural networks for tone classification and syllable recognition of Cantonese. The basic phonological structure together with those acoustic-phonetic features that are essential for Cantonese syllable recognition are also discussed.<<ETX>>

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

[2] Lokendra Shastri,et al. Learning Phonetic Features Using Connectionist Networks , 1987, IJCAI.

[3] Richard Lippmann,et al. Review of Neural Networks for Speech Recognition , 1989, Neural Computation.

[4] Jan P. van Hemert,et al. Automatic segmentation of speech , 1991, IEEE Trans. Signal Process..

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

[6] Daniel Jones,et al. A Cantonese phonetic reader , 1912 .

[7] S. Chiba,et al. Dynamic programming algorithm optimization for spoken word recognition , 1978 .

[8] P. C. Ching,et al. An NN based tone classifier for Cantonese , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[9] Lawrence R. Rabiner,et al. A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[10] L. R. Rabiner,et al. On the use of hidden Markov models for speaker-independent recognition of isolated words from a medium-size vocabulary , 1984, AT&T Bell Laboratories Technical Journal.

[11] Lawrence R. Rabiner,et al. Connected digit recognition using a level-building DTW algorithm , 1981 .

[12] Kai-Fu Lee,et al. Automatic Speech Recognition , 1989 .