From Birdsong to Rumbles: Classifying Elephant Calls with Out-of-Species Embeddings

ArXi:2605.00225v1 Announce Type: cross We show that pretrained acoustic embeddings classify elephant vocalisations at a level approaching that of end-to-end supervised neural networks, without any fine-tuning of the embedding model. This result is of practical importance because annotated bioacoustic data are scarce and costly to obtain, leaving conventional supervised approaches prone to overfitting and to poor generalisation under domain shift.