A Taiwanese (Min-nan) Text-to-Speech (TTS) System Based on Automatically Generated Synthetic Units

摘要

A Taiwanese (Min-nan) Text-to-Speech (TTS) system has been constructed in this paper based on automatically generaed synthetic units by considering several specific phonetic and linguistic characteristics of Taiwanese. Some basic facts about Taiwanese useful in a TTS system is summarized, includign the issues of tone sandhi, the writen format and the others. Three functional modules, namely a text analysis module, a prosody module, and a waveform synthesis modules is described sequentially. The synthetic units in the waveform synthesis module come from 2 sources, i.e., (1) a set of isolated-uttered tonal syllables and (2) a set of designed continuous speech corpus. A HMM-based large vocabulary Taiwanese speech recognizer is used to do the forced alignment for the speech corpus. A 85.17