Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
2
2
0
This work introduces the first framework that generates plausible ancestral vocalizations, and shows that this method is the only approach that simultaneously achieves genuine generation, phylogenetic consistency, and naturalistic audio quality across both datasets.
The results show that MAST can effectively extend self-supervised audio representations from clip-level tasks to robust box-level localization across diverse bioacoustic settings, providing a practical path for biodiversity monitoring with limited labels.