Person Identification using MFCC and Vector Quantization

ABSTRACT Voice recognition is a process to identify the speaker on the basis of individual information within the speech wave. Recent development has made the voice recognition in the security system; this technique is mainly used in the speaker voice identification and control access like banking by telephone, voice dialling, and database access services. Voice recognition mainly involves two parts, one is the feature extraction and other one is the feature matching. The main approach is to isolate the speech recognition by Mel-Scale Frequency Cepstrum coefficient and Vector quantization. MFCC is used for feature extraction and vector quantization is used to minimize the amount of data to be handled. In feature matching find the vector quantized difference between input utterance of the new signal to test and codebooks stored in data base. From the VQ distortion result we can decide whether the new signal is accepted or rejected. Experimental results show the 100 percent accuracy