English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The ASVspoof challenge series was born to spearhead research in anti-spoofingfor automatic speaker verification (ASV). The two challenge editions in 2015and 2017 involved the assessment of spoofing countermeasures (CMs) in isolationfrom ASV using an equal error rate (EER) metric. While a strategic approach toassessment at the time, it has certain shortcomings. First, the CM EER is notnecessarily a reliable predictor of performance when ASV and CMs are combined.Second, the EER operating point is ill-suited to user authenticationapplications, e.g. telephone banking, characterised by a high target user priorbut a low spoofing attack prior. We aim to migrate from CM- to ASV-centricassessment with the aid of a new tandem detection cost function (t-DCF) metric.It extends the conventional DCF used in ASV research to scenarios involvingspoofing attacks. The t-DCF metric has 6 parameters: (i) false alarm and misscosts for both systems, and (ii) prior probabilities of target and spoof trials(with an implied third, nontarget prior). The study is intended to serve as aself-contained, tutorial-like presentation. We analyse with the t-DCF aselection of top-performing CM submissions to the 2015 and 2017 editions ofASVspoof, with a focus on the spoofing attack prior. Whereas there is little tochoose between countermeasure systems for lower priors, system rankings derivedwith the EER and t-DCF show differences for higher priors. We observe someranking changes. Findings support the adoption of the DCF-based metric into theroadmap for future ASVspoof challenges, and possibly for other biometricanti-spoofing evaluations.

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