Comparative Analysis of Speaker Recognition System Based on Voice Activity Detection Technique, MFCC and PLP Features

摘要

Due to rapid advancement in technology, speaker recognition systems become more robust and user friendly. The idea is to study and analyse the speech signal based on feature extraction method. This paper compares the performance of Mel-Frequency Cepstral Coefficient (MFCC) and PLP feature extraction with voice activity detection (VAD) technique. Vector Quantisation approach is used for features matching to select the combination which gives highest accuracy.