Infoscience

Report

Audio-Visual Person Verification

In this paper we investigate benefits of classifier combination for a multimodal system for personal identity verification. The system uses frontal face images and speech. We show that a sophisticated fusion strategy enables the system to outperform its facial and vocal modules when taken separately. We show that both trained linear weighted schemes and fusion by Support Vector Machine classifier leads to a significant reduction of total error rates. The complete system is tested on data from a publicly available audio-visual database according to a published protocol.

Related material