Vietnamese Text-To-Speech system with precise tone generation

Abstract

We propose a Vietnamese Text-To-Speech (VieTTS) system which is a parametric and rule-based speech synthesis system. Fundamental speech units of this system are demisyllables with Level tone. VieTTS uses a source-filter model for speech production and a Log Magnitude Approximation (LMA) filter as the vocal tract filter. We chose the Hanoi dialect for VieTTS. Tone synthesis of Vietnamese is implemented by using fundamental frequency (F0) patterns and power pattern control. F0 is the most important factor in Vietnamese tone synthesis and the power control strongly affects Broken and Drop tones. Applying power control for tone synthesis is unique for Vietnamese compared to other tonal languages such as Chinese and Thai. This new result is confirmed by listening tests with a reasonable listening correct rate.