Speaker recognition system for security applications

Abstract

Due to the rapid advances in algorithms, VLSI design and computer technology, security systems based on speaker recognition are on the verge of commercial success. Nowadays, it is obvious that speakers can be identified from their voices. In this paper, an improved strategy for Text Dependent Automatic Speaker Verification (TD-ASV) system based on Malayalam and English language has been proposed and comparison of results are discussed. The system performs on Hidden Markov Model (HMM) technique with cepstral based features. Different speech pre-processing techniques like pre-emphasis filtering, frame blocking and windowing have been used to process the speech utterances. MFCC, ΔMFCC and Δ ΔMFCC have been used to extract the features. Speaker Identification (SI) is performed using Continuous Hidden Markov Model. The performance is analyzed in terms of Percentage Correctness (PC) and accuracy and result is visualized in a confusion matrix. The system has percentage correctness of 99.71% in English and 99.71% in Malayalam language. An application with Graphical User Interface (GUI) is also developed for security purposes using the system. The system is developed using the framework of Hidden Markov Model Tool Kit (HTK).