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No paper: the model sits in the Arena's unpublished tier (shown, not ranked).

LaST-Net (Length-Aware Layer and Scale-Adaptive Temporal Network; Jun Xue, 2026): a fine-tuned fairseq XLS-R 300M front-end whose 24 transformer-layer outputs are fused by a length- and content-conditioned layer router, projected to 192-d, processed at three temporal scales (1x, 1/2, 1/4) by a length-selective kernel block and dilated depthwise residual blocks with two length-prior residual scale-exchange stages, attentive statistics pooling per scale and a 2-way MLP head. The model also takes the clip's available duration (length features). Trained on ASVspoof 2019 LA train (dev for checkpoint selection) with RawBoost-4 paired prediction consistency. Authors' released epoch-52 checkpoint. Input exactly as the authors' infer.py at --seconds 4: 16 kHz, no normalisation, first 64000 samples (4 s), shorter clips repeated (np.tile) and cropped, available seconds = min(len, 64000)/16000 passed to the model. score = log_softmax(logits)[:, 1] (the authors' bonafide_log_score). FP32 (TF32 off).

  • Weights: not re-hosted (the authors grant no license for them). Get the authors' checkpoint; its sha256 is in the meta.yaml notes.
  • Params: 316.96 M. Trained on ASVspoof 2019 LA train (dev for selection); the Arena's ASVspoof sets are eval partitions.
  • Score: higher = bona fide. J-SPAW_LA was scored with the PyTorch wrapper; most other datasets with the TensorRT drop-in class (FP32 on the RTX 4070 Ti SUPER; FP32 on the RTX 5060 Ti), which matched PyTorch on the full J-SPAW_LA set (|dEER| <= 0.25, Spearman >= 0.999); the RTX 4060 Ti cards ran PyTorch.

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% 0.09 on ASVspoof2019_LA EER% 6.01 on ASVspoof2021_LA EER% 2.7 on ASVspoof2021_DF EER% 21.86 on ASVspoof5 EER% 6.47 on InTheWild EER% 18.18 on ADD22_eval_31 EER% 23.43 on ADD2023_track12_test_r1 EER% 18.59 on CFAD EER% 26.36 on CD-ADD EER% 18.89 on CVoiceFake_small EER% 26.98 on DeepVoice EER% 2.73 on LibriSeVoc EER% 29.29 on SONAR EER% 24.66 on ArAD EER% 16.08 on DECRO EER% 14.5 on J-SPAW_LA EER% 25.64 on ODSS EER% 3.16 on HABLA EER% 9.91 on DFADD EER% 7.71 on PyAra EER% 21.35 on XMAD EER% 0.5 on EmoFake_test SRR COMPLEMENT 62.81 on EmoSpoofTTS SRR COMPLEMENT 21.51 on LRLspoof

Downloads last month
188
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support