Real time speaker recognition of letter ‘zha’ in Tamil language

Abstract

The aim of this paper is speaker recognition of the letter `zha' in Tamil language, which consists of comparing a speech signal from an unknown speaker to a known speaker. The speech signals of the letter `zha' of male and female speakers are recognized by the Vector Quantization (VQ) technique called Mel Frequency Cepstrum Coefficients (MFCC). The recorded sampling frequency was at 16 kHz and the bit rate was at 15450 bits per second, where the original bit rate was at 128K bits per second with the help of wave surfer audio tool. The real time recognized output is taken by using Finite Fourier Transform (FFT) and this result is compared by using Mel Frequency Cepstral coefficients and vector Quantization. The speaker recognition system results are analyzed in MATLAB.