Title: "Mel Spectrum Analysis of Speech Recognition using Single Microphone "

Page(s): 15 - 20
Authors: Lakshmi S.A,Cholavendan M


Abstract: - Digital processing of speech signal is very important for high speed and precise automatic speech recognition technology. Speech recognition is the process in which certain words of a particular speaker will automatically recognized that are based on the information included in individual speech waves. Nowadays it is being used for health care, telephony military and people with disabilities therefore the digital signal processes such as feature extraction and feature matching are used for speech recognition. Inorder to extract the valuable information from speech signal, the data needs to be manipulated and analyzed. Basic method used for extracting the features of the speech signal is to find the Mel Frequency Cepstral Coefficients (MFCC) and Mel Energy Dynamic Coefficients (MEDC).In this project, speech is recognised using single microphone based on the Mel spectrum analysis. This technique basically exploits the certain features of speech. MFCC and MEDC are used for extracting the features of speech and Dynamic Time Warping (DTW) is used for feature matching. The experimental results were analysed with the help of MATLAB and the results are simulated.

Keywords-Mel frequency Cepstral Coefficients (MFCC), Mel Energy Dynamic Coefficients (MEDC), Dynamic Time Warping (DTW)..