Snap Speaker Nulling Deepfake Detection

Detect speech deepfakes by decomposing features into speaker, artifact, and context subspaces—nulling speaker information via PCA projection to isolate artifact patterns. Train minimal logistic regression classifier on orthogonally-projected representations, achieving 56% error reduction while maintaining cross-speaker and cross-TTS generalization.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit cd1c2fa808

Frequently asked questions

npx get-skill add adu2021/snap-speaker-nulling-deepfake-detection