Acoustic parameters and phonological rules of a text-to-speech system for Chinese

Abstract

A multi-language text-to-speech system developed by Carlson and Granström was used to do text-to-speech conversion for Chinese. Both phonological rules and acoustic parameters are refined. The light tone and some tone modification rules and er-colored final rules are newly introduced. It is shown that the shorten duration is most important feature for light tone syllables; and the principle of that the main vowel in the final should be pronounced with retroflex vowel [δr] simultaneously can be used for synthesizing er-colored finals.