SNAP: Speaker Nulling for Artifact Projection in Speech Deepfake Detection
Paper • 2603.20686 • Published • 2
Jihwan Kim
navvh
AI & ML interests
None yet
Recent Activity
upvoted a paper about 16 hours ago
2Xplat: Two Experts Are Better Than One Generalist upvoted a paper about 16 hours ago
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model upvoted a paper about 16 hours ago
Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World ModelsOrganizations
None yet
authored a
paper 1 day ago