Adaptive Compression and Targeted Perturbation: A Unified Framework for Generalized Audio Deepfake Detection
Open paper
Benchmark
Model
Rank
Results
audio-deepfake-detection-on-asvspoof-2021
Whisper-base + AAFI + Mel-BAP
–
21LA EER: 1.30
audio-deepfake-detection-on-asvspoof-2021
Whisper-small + AAFI + Mel-BAP
–
21LA EER: 1.12
Rank counts only results with a code link.