Publication Details
Detecting Spoofing Attacks Using VGG and SincNet: BUT-Omilia Submission to ASVspoof 2019 Challenge
Stafylakis Themos
ATHANASOPOULOU, G.
Rohdin Johan Andréas, M.Sc., Ph.D. (DCGM)
GKINIS, I.
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
detecting. spoofing, challenge, AVSSpoof
In this paper, we present the system description of the joint effortsof Brno University of Technology (BUT) and Omilia -Conversational Intelligence for the ASVSpoof2019 Spoofingand Countermeasures Challenge. The primary submission forPhysical access (PA) is a fusion of two VGG networks, trainedon single and two-channels features. For Logical access (LA),our primary system is a fusion of VGG and the recently introducedSincNet architecture. The results on PA show thatthe proposed networks yield very competitive performance inall conditions and achieved 86 % relative improvement comparedto the official baseline. On the other hand, the results onLA showed that although the proposed architecture and trainingstrategy performs very well on certain spoofing attacks, it failsto generalize to certain attacks that are unseen during training.
@inproceedings{BUT159993,
author="ZEINALI, H. and STAFYLAKIS, T. and ATHANASOPOULOU, G. and ROHDIN, J. and GKINIS, I. and BURGET, L. and ČERNOCKÝ, J.",
title="Detecting Spoofing Attacks Using VGG and SincNet: BUT-Omilia Submission to ASVspoof 2019 Challenge",
booktitle="Proceedings of Interspeech",
year="2019",
journal="Proceedings of Interspeech",
volume="2019",
number="9",
pages="1073--1077",
publisher="International Speech Communication Association",
address="Graz",
doi="10.21437/Interspeech.2019-2892",
issn="1990-9772",
url="https://www.isca-speech.org/archive/Interspeech_2019/pdfs/2892.pdf"
}