Sarika Hegde and Surendra Shetty

Automatic Speech Recognition (ASR) involves mainly two steps; feature extraction and classification (pattern recognition). Mel Frequency Cepstral Coefficient (MFCC) is used as one of the prominent featureextraction techniques in ASR. Usually, the set of all 12 MFCC coefficients is used as the feature vector inthe classification step. But the question is whether the same or improved classification accuracy can beachieved by using a subset of 12 MFCC as feature vector. In this paper, Fisher’s ratio technique is used forselecting a subset of 12 MFCC coefficients that contribute more in discriminating a pattern. The selected oefficients are used in classification with Hidden Markov Model (HMM) algorithm. The classification ccuracies that we get by using 12 coefficients and by using the selected coefficients are compared.

Automatic Speech Recognition, Statistical Technique, Fisher’s Ratio, Hidden Markov Model, Mel requency Cepstral Coeffecients (MFCC), Classification