ReTA improves open-set deepfake audio source attribution by learning reconstruction error distributions and computing per-class reject thresholds automatically.
To address this challenge, we propose a novel adaptive threshold framework named ReTA
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reject Threshold Adaptation for Open-Set Model Attribution of Deepfake Audio
ReTA improves open-set deepfake audio source attribution by learning reconstruction error distributions and computing per-class reject thresholds automatically.