CONF sby98e/IDIAP Audio-Visual Person Verification Ben-Yacoub, Souheil Luettin, Juergen Jonsson, K. Matas, J. Kittler, J. EXTERNAL http://publications.idiap.ch/attachments/reports/1998/rr98-18.pdf PUBLIC http://publications.idiap.ch/index.php/publications/showcite/sby98b Related documents Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 1999, Fort Collins, USA 1999 IDIAP-RR 98-18 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 seperately. 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. REPORT sby98b/IDIAP Audio-Visual Person Verification Ben-Yacoub, Souheil Luettin, Juergen Jonsson, K. Matas, J. Kittler, J. EXTERNAL http://publications.idiap.ch/attachments/reports/1998/rr98-18.pdf PUBLIC Idiap-RR-18-1998 1998 IDIAP IEEE Proceedings of Computer Vision and Pattern Recognition 1999. Published in IEEE Proceedings of CVPR'99, Fort Collins, USA 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.