all AI news
Transferable Models for Bioacoustics with Human Language Supervision. (arXiv:2308.04978v1 [cs.LG])
cs.LG updates on arXiv.org arxiv.org
Passive acoustic monitoring offers a scalable, non-invasive method for
tracking global biodiversity and anthropogenic impacts on species. Although
deep learning has become a vital tool for processing this data, current models
are inflexible, typically cover only a handful of species, and are limited by
data scarcity. In this work, we propose BioLingual, a new model for
bioacoustics based on contrastive language-audio pretraining. We first
aggregate bioacoustic archives into a language-audio dataset, called
AnimalSpeak, with over a million audio-caption pairs holding …
arxiv become biodiversity current data deep learning global human impacts language monitoring processing scalable supervision tool tracking vital work