USTC System for Blizzard Challenge 2006 an Improved HMM-based Speech Synthesis Method

Abstract

This paper introduces the USTC speech synthesis system for Blizzard Challenge 2006. The HMM-based parametric synthesis approach was adopted for its convenience and effectiveness in building a new voice, especially for the nonnative developers. Some useful techniques were also integrated into our system, such as minimum generation error (MGE) training, phone duration modeling and linear spectral pair (LSP) based formant enhancement. The evaluation results show that the proposed system is able to synthesize speech with high naturalness and intelligibility by using either full database or only ARCTIC subset. 1.