Selective Fusion for Speaker Verification in Surveillance
Yosef Solewicz and Moshe Koppel
In: IEEE International Conference on Intelligence and Security Informatics, 19-20 May 2005, Atlanta, USA.

Abstract

This paper presents an improved speaker verification technique that is especially appropriate for surveillance scenarios. The main idea is a meta-learning scheme aimed at improving fusion of low- and high-level speech in-formation. While some existing systems fuse several classifier outputs, the pro-posed method uses a selective fusion scheme that takes into account conveying channel, speaking style and speaker stress as estimated on the test utterance. Moreover, we show that simultaneously employing multi-resolution versions of regular classifiers boosts fusion performance. The proposed selective fusion method aided by multi-resolution classifiers decreases error rate by 30% over ordinary fusion.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.

[Edit]