Multimodal person verification system using face and speech

Abstract

Reliable user identification is a common requirement for almost every secure system. Biometric offer a natural and reliable solution to certain aspects of identity management by recognizing the individuals based on their inherent physical and behavior characteristics. Multimodal biometric person verification is gaining much popularity in recent years as they outperform unimodal person verification. This paper presents a person verification system using speech and face data. The verification system comprises of two classifiers whose scores are fused using sum rule after normalization. The experiments are carried out on VidTIMIT database. The experimental results show that face expert designed using Two-Dimensional Linear Discriminate Analysis and speech expert using Linear Prediction Cepstral Coefficients as feature extractor and Gaussian Mixture Model as opinion generator with 16 mixture will provide a Half Total Error Rate of 1.2%.