Speaker Accent Recognition by MFCC Using K-Nearest Neighbour Algorithm: A Different Approach

Abstract

A K-Nearest Neighbour Algorithm involving Mel-Frequency Cepstral Coefficients (MFCCs) is provided to perform Speech signal feature extraction for the task of speaker accent recognition. Mel-Frequency Cepstral Co-efficient is effectively used to perform the feature extraction of the input signal. For each input signal the mean of the MFCC matrix is used for pattern recognition .The K-nearest neighbour algorithm is based on evaluating minimum Euclidean distance measure from input data set to stored data set. Since large number of speakers of different accent are present, they can be grouped together depending upon their accent .Thus each signal coming from different group makes a distinct MFCC vector .In this paper we have compared the MFCC from global group to smaller sub groups.