Detecting Spoofing Attacks Using VGG and SincNet: BUT-Omilia Submission to ASVspoof 2019 Challenge

Hossein Zeinali, Themos Stafylakis, Georgia Athanasopoulou, Johan Rohdin, Ioannis Gkinis, Lukáš Burget, Jan Černocký


In this paper, we present the system description of the joint efforts of Brno University of Technology (BUT) and Omilia — Conversational Intelligence for the ASVSpoof2019 Spoofing and Countermeasures Challenge. The primary submission for Physical access (PA) is a fusion of two VGG networks, trained on single and two-channels features. For Logical access (LA), our primary system is a fusion of VGG and the recently introduced SincNet architecture. The results on PA show that the proposed networks yield very competitive performance in all conditions and achieved 86% relative improvement compared to the official baseline. On the other hand, the results on LA showed that although the proposed architecture and training strategy performs very well on certain spoofing attacks, it fails to generalize to certain attacks that are unseen during training.


 DOI: 10.21437/Interspeech.2019-2892

Cite as: Zeinali, H., Stafylakis, T., Athanasopoulou, G., Rohdin, J., Gkinis, I., Burget, L., Černocký, J. (2019) Detecting Spoofing Attacks Using VGG and SincNet: BUT-Omilia Submission to ASVspoof 2019 Challenge. Proc. Interspeech 2019, 1073-1077, DOI: 10.21437/Interspeech.2019-2892.


@inproceedings{Zeinali2019,
  author={Hossein Zeinali and Themos Stafylakis and Georgia Athanasopoulou and Johan Rohdin and Ioannis Gkinis and Lukáš Burget and Jan Černocký},
  title={{Detecting Spoofing Attacks Using VGG and SincNet: BUT-Omilia Submission to ASVspoof 2019 Challenge}},
  year=2019,
  booktitle={Proc. Interspeech 2019},
  pages={1073--1077},
  doi={10.21437/Interspeech.2019-2892},
  url={http://dx.doi.org/10.21437/Interspeech.2019-2892}
}