Speech Identification using MFCC Algorithm on Arm Platform

Abstract

Digital processing of speech signal and speech recognition algorithm is very important for fast and accurate automatic speech recognition technology. The speech is a signal of infinite information. A direct analysis of the complex speech signal is due to too much information contained in the signal. Therefore the digital signal processes such as feature extraction and feature matching are introduced to represent the speech signal. Several methods such as Liner Predictive Coding (LPC), Hidden Markov Model (HMM), Dynamic Time Warping (DTW) etc are used to identify a speech. The extraction and matching process is implemented right after the pre processing or filtering signal is performed. The non-parametric method for modelling the human auditory perception system, Mel Frequency Cepstral Coefficients (MFCCs) are utilize as extraction techniques. The non linear sequence alignment known as Dynamic Time Warping (DTW) has been used as speech modelling techniques. Since it’s obvious that the speech signal tends to have different temporal rate, the alignment is important to produce the better performance. This paper introduces MFCC to extract features and DTW to compare the test patterns for speech identification. In this paper, same algorithms are implemented onto ARM platform as well as MATLAB.