|
KMID : 0917520030100030225
|
|
Journal of Speech Sciences
2003 Volume.10 No. 3 p.225 ~ p.240
|
|
|
Performance Evaluation of Nonkeyword Modeling and Postprocessing for Vocabulary-independent Keyword Spotting
|
|
|
|
|
Abstract
|
|
|
|
In this paper, we develop a keyword spotting system using vocabulary-independent speech recognition technique, and investigate several non-keyword modeling and post-processing methods to improve its performance. In order to model non-keyword speech segments, monophone clustering and Gaussian Mixture Model (GMM) are considered. We employ likelihood ratio scoring method for the post-processing schemes to verify the excogitation results, an filler model, antisubword models and N-best decoding results are considered as an alternative hypothesis for likehood ratio scoring. We also examine different method to construct anti-subword models. We evaluate the performance of our system on the automatic telephone exchange service task. The results show that GMM-based non-keyword modeling yields better performance than that using monophone clusting. According to the post-processing experiment, the method using anti-keyword model based on Kullback-Leibler distance an N-best decoding method show better performance than other method, and we could reduce more than 50% of keyword recognition errors with keyword rejection rate of 5%.
|
|
|
KEYWORD
|
|
|
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|
|