A Multi-layered Approach to the Polysemy Problems in a Chinese to Taiwanese System

This paper proposes a novel approach to the polysemy problems in a Chinese to Taiwanese TTS system. Polysemy means there are words with more than one meaning or pronunciation. The correct pronunciation of a word affects the comprehensibility (or clarity) and fluency of Taiwanese speech. We have shown that using language models to solve the polysemy problems with outstanding results (J. Veronis et al., 1990). We use a layered approach to the polymesy problem of the word "no" (character in chinese) in this paper. Results show that the accuracy rate of proposed layered approach is 5% and 17.69% over language models and decision list classifier.