This paper presents the rst published results for automatic recognition of continuous Cantonese speech with very large vocabulary. The size of the vocabulary covered by this system is about the same as that encountered in the Hong Kong local Chinese newspaper, Wen Hui Bao (å×ø ). The system covers 6335 Chinese characters (r) and a large number of Chinese words (ü) can be formed by combining these Chinese characters. The input to the system is the end pointed speech waveform of a sentence or phrase, the output is the Big5 coded Chinese characters. In the development of the recognition system, we have devised new methods in 1) construction of a continuous Cantonese speech database, 2) lexical tone recognition in continuous Cantonese speech, and 3) integration of lexical tone and base syllable recognition results. The speaker dependent recognition rates for Chinese character, base syllable and lexical tone are 90.94%, 94.73% and 69.7% respectively.
[1]
Pak-Chung Ching,et al.
Tone recognition of isolated Cantonese syllables
,
1995,
IEEE Trans. Speech Audio Process..
[2]
Steve J. Young,et al.
Large vocabulary continuous speech recognition using HTK
,
1994,
Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.
[3]
Lai-Wan Chan,et al.
An RNN based speech recognition system with discriminative training
,
1995,
EUROSPEECH.
[4]
Lai-Wan Chan,et al.
Automatic recognition of Cantonese lexical tones in connected speech by multi-layer perceptron
,
1995,
EUROSPEECH.
[5]
Wendy J. Holmes,et al.
Speech Synthesis and Recognition
,
1988
.
[6]
Daniel Jones,et al.
A Cantonese phonetic reader
,
1912
.