END-TO-END ANTI-SPOOFING WITH RAWNET2

Hemlata Tak (1) , Jose Patino (1) , Massimiliano Todisco (1) , Andreas Nautsch (1) , Nicholas Evans (1) , Anthony Larcher (2)

1 Eurecom [Sophia Antipolis]
2 LIUM - Laboratoire d'Informatique de l'Université du Mans

Spoofing countermeasures aim to protect automatic speaker verification systems from attempts to manipulate their reliability with the use of spoofed speech signals. While results from the most recent ASVspoof 2019 evaluation show great potential to detect most forms of attack, some continue to evade detection. This paper reports the first application of RawNet2 to anti-spoofing. RawNet2 ingests raw audio and has potential to learn cues that are not detectable using more traditional countermeasure solutions. We describe modifications made to the original RawNet2 architecture so that it can be applied to anti-spoofing. For A17 attacks, our RawNet2 systems results are the second-best reported, while the fusion of RawNet2 and baseline countermeasures gives the secondbest results reported for the full ASVspoof 2019 logical access condition. Our results are reproducible with open source software.

Mots clés: anti-spoofing; countermeasures; presentation attack detection; automatic speaker verification

Domaines: Intelligence artificielle [cs.AI]

Hemlata Tak, Jose Patino, Massimiliano Todisco, Andreas Nautsch, Nicholas Evans, et al.. END-TO-END ANTI-SPOOFING WITH RAWNET2. ICASSP, Jun 2021, toronto, Canada. ⟨hal-03262948⟩