Analysis of impostor tests with high scores in NIST-SRE context

Abstract : In speaker recognition, performance of a system is usually estimated globally on a large set of tests, even if it is well known that some subsets of tests could show a very different behavior from the complete set. In fact, a small subset of tests could represent the main part of the reported errors. In this work, we highlight a such subset of tests, for which impostors obtain very high recognition scores. We evaluate if the problem comes from the involved speakers, from the voice excerpts or from the client model estimation technique. We also propose a strategy in order to minimize the effects of the observed phenomena on the overall performance of the system.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01320321
Contributor : Bibliothèque Universitaire Déposants Hal-Avignon <>
Submitted on : Monday, May 23, 2016 - 4:34:06 PM
Last modification on : Tuesday, July 2, 2019 - 5:38:02 PM

Identifiers

  • HAL Id : hal-01320321, version 1

Collections

Citation

Salah Eddine Mezaache, Jean-François Bonastre, Driss Matrouf. Analysis of impostor tests with high scores in NIST-SRE context. INTERSPEECH, Sep 2008, Brisbane, Australia. ⟨hal-01320321⟩

Share

Metrics

Record views

366