Shruti Kshirsagar

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.

RAG systems readily absorb and amplify ideological biases present in retrieved documents, even more so when prompts explicitly describe the ideological dimensions at play.

Quantifying the divergence between real and synthetic phoneme distributions via Kullback-Leibler divergence can pinpoint the most vulnerable phonemes for detecting audio deepfakes.