Search papers, labs, and topics across Lattice.
Brno University of Technology
3
0
2
Human listeners misclassify genuine audio as fake 77% of the time, revealing a critical vulnerability in our ability to discern deepfake speech.
Training with speaker references might seem essential, but RAT shows that models can excel in deepfake detection even when those references are absent during inference.
Deepfake speech detectors reveal surprising reliance on distinct audio cues, challenging assumptions about their decision-making processes.
