Search papers, labs, and topics across Lattice.
University of Stuttgart
3
0
4
Layer-wise decision fusion reveals that utilizing multiple layers can drastically improve fake audio detection accuracy, achieving a record low error rate.
Evidence Subspace Projection reveals how different factors influence deepfake detection decisions, providing a clearer understanding of model behavior in self-supervised learning.
The best deepfake audio detectors are surprisingly biased by audio quality, speaker gender, and language, undermining their real-world reliability.
