Introduces DSFA to turn deterministic audio features stochastic during fine-tuning and the CoSG ExtEval dataset, claiming SOTA generalization for CodecFake detection.
ADD 2023: Towards audio deepfake detection and anal- ysis in the wild,
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
-
Mitigating Proxy-to-Wild Domain Gap in Deepfake Speech
Introduces DSFA to turn deterministic audio features stochastic during fine-tuning and the CoSG ExtEval dataset, claiming SOTA generalization for CodecFake detection.