Showing cs.SDShow all
2 papers · 1 filter
cs.SD2026
Probing Speaker Identity Sensitivity in Audio Deepfake Detectors
Daniyal Kabir Dar, Arun Ross
Audio deepfake detectors are trained to distinguish genuine speech from synthetic speech and often perform well on standard benchmarks. Yet the same detector that achieves less tha…
cs.SD2026
Impact of Phonetics on Speaker Identity in Adversarial Voice Attack
Daniyal Kabir Dar, Qiben Yan, Li Xiao +1
Adversarial perturbations in speech pose a serious threat to automatic speech recognition (ASR) and speaker verification by introducing subtle waveform modifications that remain im…