MLLR adaptation for hidden semi-Markov model based speech synthesis

Abstract

This paper describes an extension of maximum likelihood linear regression (MLLR) to hidden semi-Markov model (HSMM) and presents an adaptation technique of phoneme/state duration for an HMM-based speech synthesis system using HSMMs. The HSMM-based MLLR technique can realize the simultaneous adaptation of output distributions and state duration distributions. We focus on describing mathematical aspect of the technique and derive an algorithm of MLLR adaptation for HSMMs.