Large Vocabulary Taiwanese Speech Recognition based on RCD using Acoustic Decision Tree

• Main Authors: Hsieh, Wen-Ping, 謝文萍
• Other Authors: Tseng S.T., Chu C.K.
• Format: Others
• Language: zh-TW
• Online Access: http://ndltd.ncl.edu.tw/handle/07647714439930874732

碩士 === 國立清華大學 === 統計學研究所 === 86 === In this thesis, we use HHM to deal with the problem of large vocabulary recognition task of Taiwanese. The phone units we use are right context dependent (RCD) phonemes. If we just consider the effect of inside syllable context dependency, the top 1 recognition accuracy reaches 88%. If we modify our models to include all inter-syllable context dependency, the result of top 1 recognition accuracy increases to 92.11% but the total number of states in our network increases to 4 times. To compensate the insufficient training data due to the large amount of models, we use the method of Acoustic Decision Tree to do state clustering.The total number of states decreases to 3/5, and the recognition rate also increases to 92.87%.