Selective fusion for speaker verification in surveillance

Yosef A. Solewicz, Moshe Koppel

Research output: Contribution to journalConference articlepeer-review

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 information. While some existing systems fuse several classifier outputs, the proposed 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.

Original languageEnglish
Pages (from-to)269-279
Number of pages11
JournalLecture Notes in Computer Science
Volume3495
DOIs
StatePublished - 2005
EventIEEE International Conference on Intelligence and Security Informatics, ISI 2005 - Atlanta, GA, United States
Duration: 19 May 200520 May 2005

Fingerprint

Dive into the research topics of 'Selective fusion for speaker verification in surveillance'. Together they form a unique fingerprint.

Cite this