QPAudioEraser removes a target speaker or accent from a trained audio classifier by negating and mixing final-layer weights, relabeling forget samples, and maximizing prediction entropy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Quantum-Inspired Audio Unlearning: Towards Privacy-Preserving Voice Biometrics
QPAudioEraser removes a target speaker or accent from a trained audio classifier by negating and mixing final-layer weights, relabeling forget samples, and maximizing prediction entropy.