t-DCF: a Detection Cost Function for the Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification

Abstract : The ASVspoof challenge series was born to spearhead research in anti-spoofing for automatic speaker verification (ASV). The two challenge editions in 2015 and 2017 involved the assessment of spoofing countermeasures (CMs) in isolation from ASV using an equal error rate (EER) metric. While a strategic approach to assessment at the time, it has certain shortcomings. First, the CM EER is not necessarily a reliable predic-tor of performance when ASV and CMs are combined. Second, the EER operating point is ill-suited to user authentication applications , e.g. telephone banking, characterised by a high target user prior but a low spoofing attack prior. We aim to migrate from CM-to ASV-centric assessment with the aid of a new tandem detection cost function (t-DCF) metric. It extends the conventional DCF used in ASV research to scenarios involving spoofing attacks. The t-DCF metric has 6 parameters: (i) false alarm and miss costs for both systems, and (ii) prior probabilities of target and spoof trials (with an implied third, nontar-get prior). The study is intended to serve as a self-contained, tutorial-like presentation. We analyse with the t-DCF a selection of top-performing CM submissions to the 2015 and 2017 editions of ASVspoof, with a focus on the spoofing attack prior. Whereas there is little to choose between countermeasure systems for lower priors, system rankings derived with the EER and t-DCF show differences for higher priors. We observe some ranking changes. Findings support the adoption of the DCF-based metric into the roadmap for future ASVspoof challenges, and possibly for other biometric anti-spoofing evaluations.
Liste complète des métadonnées

https://hal.inria.fr/hal-01880306
Contributeur : Md Sahidullah <>
Soumis le : lundi 24 septembre 2018 - 16:37:16
Dernière modification le : jeudi 7 février 2019 - 15:45:16
Document(s) archivé(s) le : mardi 25 décembre 2018 - 16:18:28

Fichier

tDCF_Odyssey2018.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01880306, version 1

Citation

Tomi Kinnunen, Kong Lee, Héctor Delgado, Nicholas Evans, Massimiliano Todisco, et al.. t-DCF: a Detection Cost Function for the Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification. Speaker Odyssey 2018 The Speaker and Language Recognition Workshop, Jun 2018, Les Sables d’Olonne, France. 〈hal-01880306〉

Partager

Métriques

Consultations de la notice

116

Téléchargements de fichiers

36