Baseline systems are grouped by task:
- Speech Deepfake (DF)
- Logical Access (LA)
- Physical Access (PA)
Please find more details in the evaluation plan.
Reference code is provided for the following systems:
-
Baseline-CQCC-GMM (Matlab & Python)
CQCC feature extraction with GMM classifier -
Baseline-LFCC-GMM (Matlab & Python)
LFCC feature extraction with GMM classifier -
Baseline-LFCC-LCNN (PyTorch)
LFCC feature extraction with LCNN classifier (DNN) -
Baseline-RawNet2 (PyTorch)
End-to-End DNN classifier
The following directory contains the scripts to compute EERs and other metrics:
- eval-package
Note that the key files are moved to https://www.asvspoof.org/. They will be downloaded by a script in the eval-package automatically. Please check README there.
If automatical downloading fails, please manually download the key files from https://www.asvspoof.org/.