SPEAKER VERIFICATION PERFORMANCE WITH CONSTRAINED DURATIONS

Abstract : Over the last decade speaker recognition has witnessed significant advances, with successful developments in Factor Analysis (FA) and more recently i-vectors, more than halving the error rates achieved by the classical UBM/GMM approach. However when very short duration utterances are considered, it is known that these improvements are much less. This paper begins with a review of the recent developments of i-vector systems with a focus on short test duration, in the region of 10 s or less. Experimental results are then presented showing that error rates rise from approximately 5% to 18% when the test duration is systematically reduced from 30 s to just 3 s. Interestingly , with the 30 s condition the i-vector error rate is in the region of half that of the corresponding UBM/GMM system. Nevertheless, when the test segments are just 3 seconds duration then the error rates of the 2 systems systems are very similar. All experiments relate to the short-short condition of the NIST 2008 SRE, but with the test duration systematically reduced.
Type de document :
Communication dans un congrès
International Workshop on Biometrics and Forensics, Mar 2014, Malta, Malta
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01927568
Contributeur : Anthony Larcher <>
Soumis le : lundi 19 novembre 2018 - 23:16:03
Dernière modification le : jeudi 22 novembre 2018 - 01:10:00
Document(s) archivé(s) le : mercredi 20 février 2019 - 16:52:59

Fichier

Sordo14_IWBF-1.v5.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01927568, version 1

Collections

Citation

Pablo Sordo Martínez, Benoˆıt Fauve, Anthony Larcher, John Mason. SPEAKER VERIFICATION PERFORMANCE WITH CONSTRAINED DURATIONS. International Workshop on Biometrics and Forensics, Mar 2014, Malta, Malta. 〈hal-01927568〉

Partager

Métriques

Consultations de la notice

11

Téléchargements de fichiers

4