Introduction

Speech science and technologies will be one of the few most important keys of future information science and technologies in a wireless era of digital contents. Chinese language is special in nature and requires special expertise for speech processing. Chinese language will also be the second important language in the future Internet world. This project has teamed up almost the majority of the best researchers in the area in Taiwan across seven different universities and Academia Sinica, including quite several younger generation researchers, to form an integrated research group with focused directions and well-defined missions. The international counterpart of this project is ATR of Japan as the core and five university laboratories with internationally active research programs as satellites.

This project has a theme on New Generation Speech Science and Technologies, including 3 sub-projects:
  (1) Sub-Project 1: Prosody, Tones and Text-to-speech Synthesis
  (2) Sub-Project 2: Robustness in Speech Recognition
  (3) Sub-Project 3: New Generation Spoken Language Systems