Search papers, labs, and topics across Lattice.
3
0
7
6
Human evaluations show SonicCaps captions are not only more descriptive but also significantly enhance audio retrieval performance compared to existing datasets.
A hidden bell-shaped curve in generative model training reveals exploitable membership signals that could threaten privacy.
Shrinking massive audio foundation models by up to 61x is now possible without significant performance loss, thanks to a novel self-supervised distillation approach that works directly on embeddings.
