The challenge is now ended. Results can be found at challenge result page.
Papers relevant to the SASV 2022 Challenge can be found at SASV2022 Related Publications page.
ASV (automatic speaker verification) systems are intrinsically required to reject both non-target (e.g., voice uttered by different speaker) and spoofed (e.g., synthesised or converted) inputs. However, there is little consideration for how ASV systems themselves should be adapted when they are expected to encounter spoofing attacks, nor when they operate in tandem with CMs (spoofing countermeasures), much less how both systems should be jointly optimised.
The goal of the first SASV (spoofing-aware speaker verification) challenge, a special sesscion in ISCA INTERSPEECH 2022, is to promote development of integrated systems that can perform ASV and CM simultaneously.
The baseline repository includes various packages for
Baseline2
described in the evaluation plan.Registration can be done by submitting below form.
Submissions should be made by sending an e-mail to sasv.challenge@gmail.com with an attachment containing a system description and score files for both development and the evaluation protocols. Precise submission instructions are included in the evaluation plan.
Awards will be presented to participants/teams whose systems achieve the best performance. Additional awards will be presented to participants/teams who report the most innovative methods as judged by the organisers.
Top three ranking teams will be awarded as follows:
The two participants/teams with the most innovative methods will be awarded $1,000 each.
The organising committee have received comments and technical support from the below list of advisors. Names in alphabetical order.
Please send an e-mail to sasv.challenge@gmail.com if you have any questions.