The approach uses tri-phone models as recognition sub-word unit in the acoustics and speech layer, and uses statistic language model in syntax layer which is based on bi-gram and tri-gram.

• 其中在声学语音层使用三音子模型作为基本的子词单元(sub-word unit),在词层句法层使用基于双词文法(bi-gram)和三词文法(tri-gram)的统计语言模型。