Search papers, labs, and topics across Lattice.
3
1
5
6
Speech enhancement doesn't always improve audio deepfake detection; in fact, algorithms that *reduce* perceptual speech quality can paradoxically lead to better spoof detection in noisy environments.
Quantifying the divergence between real and synthetic phoneme distributions via Kullback-Leibler divergence can pinpoint the most vulnerable phonemes for detecting audio deepfakes.
Even when overall accuracy seems balanced, audio deepfake detection models can exhibit significant gender bias, masked by standard metrics like EER.
