Minimum generation error training for HMM-based speech synthesis

Abstract

In HMM-based speech synthesis, there are two issues critical related to the MLE-based HMM training: the inconsistency between training and synthesis, and the lack of mutual constraints between static and dynamic features. In this paper, we propose minimum generation error (MGE) based HMM training method to solve these two issues. In this method, an appropriate generation error is defined, and the HMM parameters are optimized by using the generalized probabilistic descent (GPD) algorithm, with the aims to minimize the generation errors. From the experimental results, the generation errors were reduced after the MGE-based HMM training, and the quality of synthetic speech is improved. © 2006 IEEE.