A Large-Vocabulary Taiwanese (Min-nan) Speech Recognition System Based on Inter-syllabic Initial-Final Modeling and Lexicon-Tree Search

In this paper some preliminary work about Taiwanese (Min-nan) speech recognition research has been done and described. Also, we report some pioneer experimental results on an initial study about a large-vocabulary (with 20 thousand words) Taiwanese multi-syllabic word recognition system. For the speaker dependent case, 9.4% word error rate is achieved. A real-time prototype system implemented on a Pentium-II personal computer running MS-Windows95/NT is also shown to validate the approaches proposed in this paper.