An Enhanced Speech Recognition System

This paper describes the development of an efficient speech recognition system using various techniques such as Mel Frequency Cepstrum Coefficients (MFCC), Vector Quantization (VQ), Hidden Markov Model (HMM) and Autocorrelation. In this paper, a method to recognize the speech faster with more accuracy, speaker recognition is followed by speech recognition. MFCC/Autocorrelation is used to extract the characteristics from the input speech signal with respect to a particular word uttered by a particular speaker. Then HMM is used on Quantized feature vectors to identify the word by evaluating the maximum log likelihood values for the spoken word. Keywords— MFCC, VQ, HMM, log likelihood, Autocorrelation.