Paper Info
Title
Impact of Bandwidth and Channel Variation on Presentation Attack Detection for Speaker Verification
Abstract
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.
Year
DOI
Venue
2017
10.23919/BIOSIG.2017.8053510
2017 International Conference of the Biometrics Special Interest Group (BIOSIG)
Keywords
Field
DocType
channel variation,automatic speaker verification technology,presentation attack detection systems,high-quality speech data,narrowband speech,bandwidth variation,feature optimisation,spectro-temporal decomposition,feature extraction
Speaker verification,Narrowband,Computer science,Communication channel,Coding (social sciences),Speech recognition,Feature extraction,Bandwidth (signal processing),Cepstral analysis
Conference
ISBN
Citations 
PageRank 
978-1-5386-0396-3
1
0.34
References 
Authors
12
8
Name
Order
Citations
PageRank
hector delgado17810.47
Massimiliano Todisco213817.80
nicholas evans359454.41
Md. Sahidullah432624.99
Wei Ming Liu5233.89
Federico Alegre6934.74
Tomi Kinnunen7132386.67
Benoit Fauve81569.47