Large empirical study finds self-supervised pre-training then supervised post-training on mixed bioacoustics and general audio data produces the strongest encoders across 26 datasets for species classification, detection, individual ID and repertoire discovery.
Mustafa Chasmai, Alexander Shepard, Subhransu Maji, and Grant Van Horn
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AVEX: What Matters for Animal Vocalization Encoding
Large empirical study finds self-supervised pre-training then supervised post-training on mixed bioacoustics and general audio data produces the strongest encoders across 26 datasets for species classification, detection, individual ID and repertoire discovery.