Artificial Intelligence #audio deepfake detection#disentanglement
Dual-Granularity Orthogonal Disentanglement: New Framework Boosts Generalizable Audio Deepfake Detection
A new paper on arXiv proposes a dual-granularity orthogonal disentanglement framework for generalizable audio deepfake detection. The method enforces sample-level cosine orthogonality and batch-level cross-covariance regularization to avoid speaker identity leakage. Experiments show equal error rates of 1.35%, 7.88%, and 21.58% on standard benchmarks.
Jun 16, 2026 1 source
