Xeno-canto

@xeno-canto.bsky.social

20+ years! of sharing open wildlife sounds from around the world. Birds, Grasshoppers, Frogs, Bats, Land Mammals. 12k recordists, 13k species, 1 million recordings. Open data is not free! Consider a donation https://xeno-canto.org/donate

New publication about my art piece "Alakaʻi 1777", which uses a mathematical model of the syrinx to reconstruct the lost song culture of an extinct bird called the Kauaʻi ʻōʻō! This project took over the last year of my life in the best possible way ❤️ www.cambridge.org/core/journal...

Alakaʻi 1777 – using immersive sound to communicate the nonhuman cultural extinction crisis | Biotechnology Design | Cambridge Core

Alakaʻi 1777 – using immersive sound to communicate the nonhuman cultural extinction crisis - Volume 4

cambridge.org

Sorting out the history of whaling pressure on five populations of blue whales in the Indian Ocean and SW Pacific. So many years of work went into this monumental collaboration with many many coauthors. So pleased to see this paper finally published. doi.org/10.1111/mms....

Blue whale news@bluewhalenews.bsky.social · 2y ago

Published! Our huge effort to obtain catch series for each of five overlapping populations of pygmy blue whales. Big collaboration with 30+ coauthors using spatial patterns of blue whale song (unique to each population) to figure out where each resides 1/n

Excited to share our new publication in Bioacoustics today, describing the vocal repertoire of white-nosed coatis! 🐾 We combined traditional acoustic analyses with an unsupervised approach to characterise the complexity and diversity of their vocal behaviour. doi.org/10.1080/0952...

Bild

New paper: "Twelve quick tips for applying deep learning to animal sounds" https://doi.org/10.1371/journal.pcbi.1014604 - led by Burooj Ghani and Leonie Baier, distilling lots of tips & handy links based on our computational #bioacoustics recent experience

Twelve quick tips for applying deep learning to animal sounds

Deep learning is transforming the study of animal sound, enabling the automated identification of species, individuals, behaviors, and ecological patterns from large collections of recordings. While bioacoustic machine-learning models are growing more powerful, many biologists—ecologists, behavioral scientists, conservationists—and others working with acoustic data feel unprepared to navigate the computational workflows required to implement them. This article presents practical guidelines covering the full lifecycle of bioacoustic machine learning, including problem definition, data sourcing and annotation, model training, evaluation, deployment, reproducibility, and ethical considerations. Rather than providing a linear checklist, the guidelines outline an iterative framework for building science-led workflows, leveraging transfer learning and open-source tools, evaluating models based on the real-world cost of errors, and addressing domain shift under variable field conditions. Ultimately, this workflow demystifies the software-engineering process, providing a low-barrier and reproducible pathway for researchers applying machine learning to animal sound.

journals.plos.org