A Study on Utterance Verification in Chinese Keyword Spotting

• Main Authors: Huang, Kuo-Chang, 黃國彰
• Other Authors: Juang Yau-Tarng
• Format: Others
• Language: zh-TW
• Published: 1997
• Online Access: http://ndltd.ncl.edu.tw/handle/74510893636928654215

碩士 === 國立中央大學 === 電機工程學系 === 85 === In this thesis, we will search the best technique of utterance verification,using in keyword spotting system. The corpus of this thesis can divide into three parts, in the first part; we focus on increasing the recognition rate in keyword spotting system without the ability of rejection. From the experimental information, we proposed a decision rule that can rise the recognition rate from Top3 to Top1. From the experimental result, it is seem that the recognitionrate can up to 6%-7% after using the decision rule. Finally, we improve the system recognition speed about 30 times according to the rule of speeding up.In the second part, we make some utterance verification experiments based on likelihood score ratio. At the same time, the anti-keyword model is used as alternative model. By using the alternative model the better recognition resultswere obtained. In addition, another approach is proposed to generate the anti-keyword model without retrain the training data. In the final of this thesis, we integrate the front second parts to build a utterance verificationsystem with multiple parts (two-stages recognition system). The advantage is that it can modify the correct keyword path to optimal path by utterance verification in second stage if the correct keyword path doesn''t appear in Top1path in the first stage. It is found that the multiple paths of utterance verification system will perform well.