ABSTRACT

This paper presents the application based Neural Network for speaker recognition in a voice authenticated access control system in high security applications. The Neural Network designed for this purpose employs hybrid feature extraction techniques for speaker identification. These features include the time domain as well as frequency domain features and are hence named as hybrid features. Speaker dependent features obtained by Linear Predictive Coding (LPC) and Mel Frequency Cepstrum Coefficients (MFCC) have been used in this work. The hybrid features are used for testing the voice authenticated access control. The performance of different features individually and in combination has been analysed by finding recognition efficiency of speaker identification system. The proposed system uses Feed Forward Neural Network classifier. The results obtained from the hybrid features show the improvement in recognition efficiency. The work has been implemented in MATLAB environment. The experiments have been conducted with English language database and Rajasthani Language.