Pellav3: Speech Anti-Spoofing Arena wrapper

Packaged for the Speech Anti-Spoofing Arena from the authors' code.

No paper: the model sits in the Arena's unpublished tier (shown, not ranked).

Pellav3 (Sadanie, November 2026): an open-weights two-view audio deepfake detector (1.54 B parameters). Each 4 s window is read by XLS-R 1B on the standardised waveform (softmax mix of all 49 hidden states) and by w2v-BERT 2.0 on 80-bin kaldi log-mel fbank features (25-state mix); each view is projected to 256-d and refined by two Res2 blocks, the frame sequences are concatenated per frame (512-d), refined by two shared Res2 blocks and pooled by attentive statistics pooling into Linear(1024,1) -> logit(fake). Authors' released checkpoint; training data undisclosed. Input as the authors' pellav3_infer.py view(): 16 kHz, mean removal, 20 Hz high-pass (zero-phase 2nd-order Butterworth), ITU-R BS.1770 loudness normalisation to -23 LUFS (pyloudnorm semantics), zero-pad to 4 s. Arena 4 s cap: one window, the first 4 s (64000 samples) of the authors' window grid (the authors average 4 s windows every 2 s over longer clips; clips <= 4 s are scored identically). score = -logit(fake), higher = bona fide. FP32 (TF32 off; the authors run bfloat16 autocast).

Arena results

arena tier arena rank

EER% (lower is better); EmoSpoofTTS and LRLspoof are spoof-only and use 1-SRR% at the model's DeepVoice EER threshold. Per-dataset scores are under .eval_results/.

EER% 0.57 on ASVspoof2019_LA EER% 1.63 on ASVspoof2021_LA EER% 0.55 on ASVspoof2021_DF EER% 9.88 on ASVspoof5 EER% 1 on InTheWild EER% 1.08 on ADD22_eval_31 EER% 3.79 on ADD2023_track12_test_r1 EER% 9.72 on CFAD EER% 0.01 on CD-ADD EER% 5.19 on CVoiceFake_small EER% 1.91 on DeepVoice EER% 0.03 on LibriSeVoc EER% 0.04 on SONAR EER% 0.03 on ArAD EER% 0.6 on DECRO EER% 0 on J-SPAW_LA EER% 1.11 on ODSS EER% 0 on HABLA EER% 0 on DFADD EER% 0.13 on PyAra EER% 0.07 on XMAD EER% 0.1 on EmoFake_test SRR COMPLEMENT 0.03 on EmoSpoofTTS SRR COMPLEMENT 1.77 on LRLspoof

Downloads last month
213
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support