Home

Document/Press

Progress Report

Example

Online demo

Publications

Researchers

TTS Webboard
 

This project was established in 1998. The aim of our software is to create synthesized Thai speech with natural sounding accent and rhythm. The speech output is based on the concatenation of these speech units. Speech unit based on demisyllable approach has been adopted in the first phase. In the current phase, the speech synthesis is based on unit selection technique. The system is designed to be able to analyze Thai text into appropriate phrases, words and pronunciations by using an intelligent natural language processing (NLP) algorithm.

Our team aims to investigate the following main areas of research: acoustic-phonetics, corpus-base synthesis, discourse and speech synthesis, innovative speech signal processing techniques, Input annotations and text processing, prosody processing, and utterance generation.  

*** News: Vaja TTS v.5.0 (Evaluation) and its installation description can be downloaded click here***