Integrated Presentation Attack Detection and Automatic Speaker Verification: Common Features and Gaussian Back-end Fusion

Massimiliano Todisco 1 Héctor Delgado 1 Kong Lee 2 Md Sahidullah 3 Nicholas Evans 1 Tomi Kinnunen 4 Junichi Yamagishi 5, 6
1 Eurecom [Sophia Antipolis]
2 NEC Corporation
3 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
4 University of Eastern Finland
5 NII - National Institute of Informatics
6 School of Engineering [Edinburgh]
Abstract : The vulnerability of automatic speaker verification (ASV) systems to spoofing is widely acknowledged. Recent years have seen an intensification in research efforts to develop spoofing countermeasures, also known as presentation attack detection (PAD) systems. Much of this work has involved the exploration of features that discriminate reliably between bona fide and spoofed speech. While there are grounds to use different front-ends for ASV and PAD systems (they are different tasks) the use of a single front-end has obvious benefits, not least convenience and computational efficiency, especially when ASV and PAD are combined. This paper investigates the performance of a variety of different features used previously for both ASV and PAD and assesses their performance when combined for both tasks. The paper also presents a Gaussian back-end fusion approach to system combination. In contrast to cascaded architec-tures, it relies upon the modelling of the two-dimensional score distribution stemming from the combination of ASV and PAD in parallel. This approach to combination is shown to gener-alise particularly well across independent ASVspoof 2017 v2.0 development and evaluation datasets.
Keywords : spoofing i-vector automatic speaker verification GMM fusion presentation attack detection countermeasures
Type de document :
Communication dans un congrès
Interspeech 2018 - 19th Annual Conference of the International Speech Communication Association, Sep 2018, Hyderabad, India. ISCA, 〈10.21437/Interspeech.2018-2289〉
Liste complète des métadonnées
https://hal.inria.fr/hal-01889934
Contributeur : Md Sahidullah <>
Soumis le : lundi 8 octobre 2018 - 10:55:20
Dernière modification le : mardi 18 décembre 2018 - 16:38:02
Document(s) archivé(s) le : mercredi 9 janvier 2019 - 13:32:36

Fichier

integrated-presentation-attack...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

UNIV-LORRAINE | LORIA-NLPKD | LORIA | INRIA | EURECOM

Citation

Massimiliano Todisco, Héctor Delgado, Kong Lee, Md Sahidullah, Nicholas Evans, et al.. Integrated Presentation Attack Detection and Automatic Speaker Verification: Common Features and Gaussian Back-end Fusion. Interspeech 2018 - 19th Annual Conference of the International Speech Communication Association, Sep 2018, Hyderabad, India. ISCA, 〈10.21437/Interspeech.2018-2289〉. 〈hal-01889934〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

68

Téléchargements de fichiers

55

Contact


archive-ouverte@inria.fr