A system that recognizes and authenticates the voice of a user by extracting the distinct features of their voice samples is usually termed as Voice recognition system. Voice identification is carried out by converting the human voice into digital data. The digitized audio samples then undergo feature excerption process to extract Mel Frequency Cepstral Coefficients features. These coefficients are subjected to feature matching through Dynamic Time Warping to match with the patterns existing in

more »

... the database for limited Tamil words. This paper focuses on a secure system that deploys the voice recognition for a natural language (Tamil) by combining the digital and mathematical knowledge using MFCC and DTW to extract and match the features to improve the accuracy for better performance.