Continuous Speech Keyword Spotting Using Phoneme Concatenation

• Main Authors: Chen ,Shing-Huai, 陳芯暉
• Other Authors: Chung-Hsien Wu
• Format: Others
• Language: zh-TW
• Published: 1995
• Online Access: http://ndltd.ncl.edu.tw/handle/57886611966490955864

碩士 === 國立成功大學 === 資訊及電子工程研究所 === 83 === In this thesis, s Continuous Speech Keyword SPotting System Using Phoneme Template Concatenation is described, the function of this system is to extract the keyword of a sentence which is from the continuous speech input of users can define their own keyword or nonkeyword database without retraining this system. In the procedure of training, we collect 176 monosyllables for training. they are segemented into consonants and vowels. Then we train them with Bayesain Network and svae them into the referance databese. In the recognition procedure, we use the One Stage dynamic algorithm as the main skeleton of the system. In order to increase the speed and the accuracy of recognition, we propose several useful methods. Lastly, we nornalize the accomulated distortion to decide the best recsult. In our experimemts, we collect 30 place names in the South of Taiwan as the keywords and 20 kprobable inquiry words as the nonkeywords to simulate the system. Experimental results show that the average pertage of accuracy is 86.3%.