Raw differentiable architecture search for speech deepfake and spoofing detection

Ge, Wanying; Patino, Jose; Todisco, Massimiliano; Evans, Nicholas
ASVspoof 2021, Automatic Speaker Verification
Spoofing And Countermeasures Challenge, 16 September 2021

End-to-end approaches to anti-spoofing, especially those which operate directly upon the raw signal, are starting to be competitive with their more traditional counterparts. Until recently, all such approaches consider only the learning of network parameters; the network architecture is still hand crafted. This too, however, can also be learned. Described in this paper is our attempt to learn automatically the network architecture of a speech deepfake and spoofing detection solution, while jointly optimising other network components and parameters, such as the first convolutional layer which operates on raw signal inputs. The resulting raw differentiable architecture search system delivers a tandem detection cost function score of 0.0517 for the ASVspoof 2019 logical access database, a result which is among the best single-system results reported to date.


DOI
HAL
Type:
Conférence
Date:
2021-09-16
Department:
Sécurité numérique
Eurecom Ref:
6611
Copyright:
© ISCA. Personal use of this material is permitted. The definitive version of this paper was published in ASVspoof 2021, Automatic Speaker Verification
Spoofing And Countermeasures Challenge, 16 September 2021 and is available at : http://dx.doi.org/10.21437/ASVSPOOF.2021-4

PERMALINK : https://www.eurecom.fr/publication/6611