Speaker recognition system using mel-frequency cepstrum coefficients, linear prediction coding and vector quantization

Identity verification is very important issue in current era of information technology. Conventional means of identity verification using keys or personal identification numbers and passwords can be stolen and are not well suited for such critical purposes. To overcome this problem new bio metric verification method have been e m e r g e d. Now, the i n c r e a s ed computing power and decreased microchip size has given thrust for implementing realistic biometric authentication systems such as speech recognition system. In this paper, authors implemented a speaker recognition system (SRS) using Mel-Frequency Cepstrum Coefficients (MFCC), Linear Prediction Coding (LPC) as feature extraction techniques and Vector Quantization (VQ) as speaker classification technique.