The International Journal of Innovative Research in Computer and Communication Engineering
Automatic speech recognition system consists of two stages: one is pre-processing stage and another one is classification stage. In pre-processing stage continuous speech signal is recorded and segmented. The classification stage is used to classify the extracted features. The segmentation algorithm is hybrid of short time energy and spectral centroid. It has high segmentation accuracy. The hit rate is 95.33% and false alarm rate is 4.67%. In this paper, MFCC is used for feature extraction and ELM, KNN classifiers are used for speech classification. Compare to KNN classifier ELM classifier has high classification accuracy.