SVM based Arabic speaker verification system for mobile devices

Abstract

User authentication is very critical to ensure only allowed users are able to access restricted resources. Voiceprint can be used as a unique password of the user to prove his/her identity. In this paper, we propose a text-dependent speaker verification system for Arabic language. The paper advocates the use of discrete representation of speech signals in terms of Mel-frequency cepstral coefficients (MFCCs), linear predictive coding (LPC) and perceptual linear prediction (PLP) as input features for the system and proposes the use of support vector machine (SVM) to recognize authorized user and unlock devices for him/her. Furthermore, the paper introduces the use of Relative Spectral Transformation filter (Rasta) to support Perceptual Linear Prediction (PLP) preprocessing. The paper describes system components and demonstrates how it works. It presents the performance of our system using different kernel functions and analyzes the system's results.