HMM speech recognition using stochastic language models.
Kenji Kita, Takeshi Kawabata, Toshiyuki Hanazawa · Journal of the Acoustical Society of Japan (E) · 1991
One of the major reasons for using language models in speech recognition is to reduce the search space.Context-free grammars or finite state grammars are suitable for this purpose.However, these models ignore the stochastic characteristics of a language.In this paper, three stochastic language models are investigated.These models are 1) a trigram model of Japanese syllables, 2) a stochastic shift/reduce model in LR parsing, and 3) a trigram model of context-free rewriting rules.These stochastic language models are incorporated into the syntax-directed HMM-based speech recognition system, and tested by phrase recognition experiments.The phrase recognition rate is improved from 88.2% to 93.2%.