List your company
ResearchFormerly WizWand

Audio Deepfake Detection on ASVspoof 2024 (EER)

7.38EERProSDD
5.930815.712925.49535.2771Mar 6, 2026Mar 12, 2026Mar 19, 2026Mar 25, 2026Apr 1, 2026Apr 7, 2026Apr 14, 2026
Updated 6mo ago

Evaluation results

MethodLinks
ProSDDTraining Setting=Trained on ASVspoof 20242026.047.38
W2V2-AASISTTraining Protocol=Protocol 2 (multi-dataset), Model Scale=317M2026.0311.31
DF-Arena 500MTraining Protocol=Protocol 2 (multi-dataset), Model Scale=500M2026.0312.39
W2V2-TCMTraining Protocol=Protocol 2 (multi-dataset), Model Scale=319M2026.0313.81
MoLEXTraining Protocol=Protocol 2 (multi-dataset), Model Scale=376M2026.0315.87
mHuBERT-Iter2Training Protocol=Protocol 2 (multi-dataset), Model Scale=100M2026.0316.01
ResembleAI-2BTraining Protocol=Protocol 2 (multi-dataset), Model Scale=2000M2026.0316.29
mHuBERT-FinalTraining Protocol=Protocol 2 (multi-dataset), Model Scale=100M2026.0316.88
mHuBERT-Iter1Training Protocol=Protocol 2 (multi-dataset), Model Scale=100M2026.0317.55
WavLM-Base+Training Protocol=Protocol 2 (multi-dataset), Model Scale=100M2026.0318.45
HuBERT-BaseTraining Protocol=Protocol 2 (multi-dataset), Model Scale=100M2026.0319.52
DF-Arena 100M-V1Training Protocol=Protocol 2 (multi-dataset), Model Scale=100M2026.0321.39
WavLM-BaseTraining Protocol=Protocol 2 (multi-dataset), Model Scale=100M2026.0321.62
AASISTTraining Setting=Trained on ASVspoof 20242026.0425.77
XLSR-SLSTraining Setting=Trained on ASVspoof 20242026.0439.62
RawNet2Training Setting=Trained on ASVspoof 20242026.0443.61