Tibetan Language Continuous Speech Recognition Based on Dynamic Bayesian Network

Dynamic Bayesian Networks (DBN) area subset of the probabilistic graphical models (PGM) which include hidden Markov model (HMM) as a special case. One of the principle weaknesses of HMMs is the independence assumptions on the observed and hidden processes of speech. This paper proposed to use the DBN for Tibetan language continuous speech recognition.The proposed approach is based on structure learning paradigm in DBN framework. This approach has the advantage to guaranty that the resulting model represents speech with higher fidelity than HMM. The results of recognition experiments show that the proposed algorithm has better performance of recognition rate and noise suppression compared with HMM.