SingFake

The 'SingFake' dataset/benchmark contains synthetic speech samples and is used to evaluate the generalization capabilities of models in detecting and attributing synthetic speech generated by unseen sources.

Papers using SingFake (3)

Bridging Attribution and Open-Set Detection using Graph-Augmented Instance Learning in Synthetic Speech2026SVDD 2024: The Inaugural Singing Voice Deepfake Detection Challenge2024 · 11 citesSinging Voice Graph Modeling for SingFake Detection2024