A BAYESIAN APPROACH TO HMM-BASED SPEECH SYNTHESIS

This paper proposes a new framework of speech synthesis based on the Bayesian approach. The Bayesian method is a statistical tech-nique for estimating reliable predictive distributions by marginaliz-ing model parameters. In the proposed framework, all processes for constructing the system can be derived from one single predictive distribution which represents the basic problem of speech synthesis directly. Using HMM as the likelihood function and assuming some approximations, it can be regarded as an application of the varia-tional Bayesian method to the HMM-based speech synthesis. Ex-perimental results show that the proposed method outperforms the conventional one in a subjective test. Index Terms — HMM-based speech synthesis, variational Bayesian method, prior distribution, cross validation, context clus-tering 1