一作ACL 2026Findings· Findings of ACL
A Unified Feature Mixture Framework for Joint Speech and Singing Deepfake Detection
Aastha Sharma · Guangjing Wang
摘要
High-fidelity audio generation techniques, such as voice conversion and singing voice synthesis, have significantly increased the risk of audio deepfakes. Although existing methods perform well on conversational speech deepfake detection, they fail severely under the speech-to-singing domain shif...