The HTS-2008 System: Yet Another Evaluation of the Speaker-Adaptive HMM-based Speech Synthesis System in The 2008 Blizzard Challenge

Abstract

For the 2008 Blizzard Challenge, we used the same speaker-adaptive approach to HMM-based speech synthesis that was used in the HTS entry to the 2007 challenge, but an improved system was built in which the multi-accented English average voice model was trained on 41 hours of speech data with high-order mel-cepstral analysis using an efficient forward-backward algorithm for the HSMM. The listener evaluation scores for the synthetic speech generated from this system was much better than in 2007: the system had the equal best naturalness on the small English data set and the equal best intelligibility on both small and large data sets for English, and had the equal best naturalness on the Mandarin data. In fact, the English system was found to be as intelligible as human speech.