IMPOSTURE CLASSIFICATION FOR TEXT-DEPENDENT SPEAKER VERIFICATION

Abstract : This work focuses on text-dependent speaker verification, where a user is required to chose and pronounce a customized pass-phrase to get authenticated. In this context, there are three types of impos-tures: an impostor pronouncing the correct pass-phrase, an impostor pronouncing a wrong pass-phrase and the most difficult one: an impostor playing back a recording of the target speaker pronouncing a wrong pass-phrase. Detecting and classifying different types of im-postures can help to prevent future impostures of the same type. In this work, we first propose a new verification score to reject Play-back impostures. This score allows a relative reduction of 90% of the equal error rate against Playback impostures while offering performance similar to the baseline text-dependent score against other types of impostures. As a second contribution, we show that the new score can be combined with an existing text-dependent verification score to improve the classification of the different types of impos-tures. The performance of the speaker verification engine for impos-ture classification is significantly improved with the C llr decreasing by at least 29% compared to the original system.
Type de document :
Communication dans un congrès
IEEE International Conference on Acoustic Speech and Signal Processing (ICASSP), May 2014, Florence, Italy
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01927570
Contributeur : Anthony Larcher <>
Soumis le : lundi 19 novembre 2018 - 23:20:08
Dernière modification le : jeudi 22 novembre 2018 - 01:10:00

Fichier

Icassp14_Dual_Scoring_v1.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01927570, version 1

Collections

Citation

Anthony Larcher, Kong Aik Lee, Bin Ma, Haizhou Li. IMPOSTURE CLASSIFICATION FOR TEXT-DEPENDENT SPEAKER VERIFICATION. IEEE International Conference on Acoustic Speech and Signal Processing (ICASSP), May 2014, Florence, Italy. 〈hal-01927570〉

Partager

Métriques

Consultations de la notice

7

Téléchargements de fichiers

3