Acoustic modeling based on Chinese phonetics knowledge

This paper presents research on using Chinese phonetics knowledge in acoustic modeling based on extended initial/final (XIF). Context-dependent (CD) model is required for the improvement in performance of the acoustic model, and decision tree-based state tying technology is used to solve the problem which is the huge number of the modelpsilas parameters. Chinese phonetics knowledge plays an important role in designing the question set for the decision tree. Experiment results show that making full use of Chinese phonetics knowledge in designing decision tree question set makes the clustering procedure more reasonable and appropriate, and effectively improves recognition performance of acoustic model.