Impact of Bandwidth and Channel Variation on Presentation Attack Detection for Speaker Verification

Vulnerabilities to presentation attacks can undermine confidence in automatic speaker verification (ASV) technology. While efforts to develop countermeasures, known as presentation attack detection (PAD) systems, are now under way, the majority of past work has been performed with high-quality speec...

Full description

Saved in:
Bibliographic Details
Main Authors: Delgado, Hector, Todisco, Massimiliano, Evans, Nicholas, Sahidullah, Md, Wei Ming Liu, Alegre, Federico, Kinnunen, Tomi, Fauve, Benoit
Format: Conference Proceeding
Language:English
Subjects:
Cepstral analysis
Narrowband
Niobium
Speech
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Vulnerabilities to presentation attacks can undermine confidence in automatic speaker verification (ASV) technology. While efforts to develop countermeasures, known as presentation attack detection (PAD) systems, are now under way, the majority of past work has been performed with high-quality speech data. Many practical ASV applications are narrowband and encompass various coding and other channel effects. PAD performance is largely untested in such scenarios. This paper reports an assessment of the impact of bandwidth and channel variation on PAD performance. Assessments using two current PAD solutions and two standard databases show that they provoke significant degradations in performance. Encouragingly, relative performance improvements of 98% can nonetheless be achieved through feature optimisation. This performance gain is achieved by optimising the spectro-temporal decomposition in the feature extraction process to compensate for narrowband speech. However, compensating for channel variation is considerably more challenging.
ISSN:1617-5468
DOI:10.23919/BIOSIG.2017.8053510