9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

Bi-Gaussian Score Equalization in an Audio-Visual SVM-Based Person Verification System

Pascual Ejarque, Javier Hernando

Universitat Politècnica de Catalunya, Spain

In multimodal fusion systems a normalization of the features or the scores is needed before the fusion process. In this work, in addition to the conventional methods, histogram equalization, which was recently introduced by the authors in multimodal systems, and Bi-Gaussian equalization, which takes into account the separate statistics of the genuine and impostor scores, and is introduced in this paper, are applied upon the scores in a multimodal SVM-based person verification system composed by prosodic, speech spectrum, and face information. Bi-Gaussian equalization has obtained the best results and outperform in more than a 23.25% the results obtained by Min-Max normalization.

Full Paper

Bibliographic reference.  Ejarque, Pascual / Hernando, Javier (2008): "Bi-Gaussian score equalization in an audio-visual SVM-based person verification system", In INTERSPEECH-2008, 2663-2666.