Text independent automatic speaker recognition system in Malayalam

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. In this thesis, an improved strategy for Text Tndependent Automatic Speaker Verification (TI-ASV) system based on Malayalam has been proposed and results are observed. The system performs on Gaussian Mixture Model (GMM) 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 ΔΔMFCC have been used to extract the features. Speaker identification is performed using Continuous Hidden Markov Model. The performance is analyzed in terms of Percentage Correctness (PC) and accuracy. 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).

I. Introduction

Speech communication is the most natural means of communication between humans without any tools or any explicit education. Despite all our novel means of communication, like e-mail and chat, speech is still the best means of communication, a fact once again proven by the immense popularity of cellular phone. The advent of efficient Digital Signal Processing (DSP) algorithms and fast digital computers for the implementation, has seen a tremendous rise in the growth of speaker recognition systems.