A Hybrid HMM/BN Acoustic Model for Automatic Speech Recognition

Konstantin MARKOV  Satoshi NAKAMURA  

IEICE TRANSACTIONS on Information and Systems   Vol.E86-D   No.3   pp.438-445
Publication Date: 2003/03/01
Online ISSN: 
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Issue on Speech Information Processing)
Category: Speech and Speaker Recognition
automatic speech recognition,  Bayesian networks,  acoustic modeling,  HMM,  

Full Text: PDF>>
Buy this Article

In current HMM based speech recognition systems, it is difficult to supplement acoustic spectrum features with additional information such as pitch, gender, articulator positions, etc. On the other hand, Bayesian Networks (BN) allow for easy combination of different continuous as well as discrete features by exploring conditional dependencies between them. However, the lack of efficient algorithms has limited their application in continuous speech recognition. In this paper we propose new acoustic model, where HMM are used for modeling of temporal speech characteristics and state probability model is represented by BN. In our experimental system based on HMM/BN model, in addition to speech observation variable, state BN has two more (hidden) variables representing noise type and SNR value. Evaluation results on AURORA2 database showed 36.4% word error rate reduction for closed noise test which is comparable with other much more complex systems utilizing effective adaptation and noise robust methods.