A high-performance Min-Nan/Taiwanese TTS system

Abstract

In this paper, the implementation of a high-performance Min-Nan/Taiwanese TTS system is presented. The system can convert both Min-Nan/Taiwanese texts, represented in a hybrid Han-Lo written form, and Chinese texts into natural Taiwanese speeches. It is an improved version of the system developed previously [11]. Improvements include: the add of a "Chinese-to-Min-Nan/Taiwanese" lexicon to solve the OOV problem and to increase the ability of processing Chinese text; the use of explicit tone sandhi rules to ease the learning of prosody generation; a further processing of the training database to detect all breaks not associated with PMs; and the use of four RNNs to separately generate four types of prosodic parameters. The system is implemented by software and runs in real-time on PC. An informal subjective listening test confirmed that the system performed well. All synthetic speeches sounded natural for well-tokenized Min-Nan/Taiwanese texts and for automatic tokenized Chinese texts.