The speech recognition system for all the Chinese syllables usinghidden Markov model

摘要

A speech recognition system for all the Chinese syllables isdescribed. The system is a hidden Markov model (HMM)-based recognizerusing the initial consonant and the final vowel as the recognition unitwith various features derived from linear predictive coding cepstralcoefficients. In order to deal with the difficulties introduced byvariabilities of speech, the authors transformed a cepstral for a voweland a multimodel for a consonant. Each element is represented by ahidden Markov model. It is shown that the HMM alone is inadequate insuch a difficult task. A syllable recognition accuracy of 93% for aspeaker-dependent test is reported. The feasibility of the system isshown