期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：4
DOI：10.15680/ijircce.2015.0304124
出版社：S&S Publications
摘要：Automatic speech recognition system consist of two stages: One is Pre-processing stage and another oneis classification stage. In pre processing stage continuous speech signal is recorded and segmented. The classificationstage is used to classify the extracted features. The segmentation algorithm is hybrid of short time energy and spectralcentroid. It has high segmentation accuracy. The Hit Rate rate is 95.33% and False Alarm rate is 4.67%. In this paperMFCC is used for feature extraction and ELM, KNN classifiers are used for speech classification. Compare to KNNclassifier ELM classifier has high classification accuracy
关键词：Speech segmentation; Spectral Centroid; Speech Classification; KNN; ELM
