In order to use duration information in Language IDentification (LID) efficiently, the inhomogeneous Hidden Markov Model (HMM) with general topological structure is proposed, and is used to identify the language between Mandarin and English also.
英
美
- 為了充分利用語(yǔ)音信號中的段長(cháng)信息,該文提出了一種具有一般拓撲結構的非齊次隱含Markov模型(Hidden Markov Model,HMM),并將其應用于中、英文語(yǔ)種辨識(Language IDentification,LID)系統。
