Uyghur continuous speech recognition system based on HMM

Abstract

Uyghur language is an agglutinative language.It is possible to produce a very large number of words from the same root with suffixes,so that the speech recognition of Uyghur language is very difficult.Combined with the characteristics of Uyghur language,this paper built a Uyghur continuous speech database,and designed the Hidden Markov Model(HMM) based Uyghur continuous speech recognition system by using the HTK(HMMToolKit).On the acoustic level,this paper selected triphone as the basic recognition unit,and used many methods such as decision tree,tied-state triphones,fixing the silence models,increasing Gaussian mixture distribution to improve the precision of the models.On the language level,this study used the statistics-based bigram language model.Finally,this paper presented some recognition experiments by using that system.