Diffusion reconstruction creates hard samples for audio deepfake detection training, and when paired with feature aggregation and RACL, it reduces average EER versus baselines.
Crucially, the model achieves con- sistent gains over the baseline across all individual spoofing methods in the evaluated subsets
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Diffusion Reconstruction towards Generalizable Audio Deepfake Detection
Diffusion reconstruction creates hard samples for audio deepfake detection training, and when paired with feature aggregation and RACL, it reduces average EER versus baselines.