Pretrained out-of-species embeddings from models like Perch achieve AUCs of 0.849-0.936 on African and Asian elephant calls, within 2.2% of end-to-end supervised systems, with early transformer layers sufficing for compact on-device use.
Wood, Maximilian Eibl, and Holger Klinck
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Curates over 900 hours of SRKW acoustic data plus other marine mammal recordings via positive-unlabeled active learning, releasing transformer classifiers that report AUROC 0.58-0.77 and species top-1 accuracy of 53.2% on held-out benchmarks.
Bacpipe is a modular Python package that integrates state-of-the-art bioacoustic deep learning models to generate embeddings, classifier predictions, and evaluation pipelines for custom audio data.
The paper introduces CoarseSoundNet, a deep learning model for classifying biophony, geophony, and anthropophony in passive acoustic monitoring recordings, reporting performance gains from additional similar data, a silence class, and decision thresholds, plus a case study on acoustic index trends.
citing papers explorer
-
From Birdsong to Rumbles: Classifying Elephant Calls with Out-of-Species Embeddings
Pretrained out-of-species embeddings from models like Perch achieve AUCs of 0.849-0.936 on African and Asian elephant calls, within 2.2% of end-to-end supervised systems, with early transformer layers sufficing for compact on-device use.
-
Positive-Unlabelled Active Learning to Curate a Dataset for Orca Resident Interpretation
Curates over 900 hours of SRKW acoustic data plus other marine mammal recordings via positive-unlabeled active learning, releasing transformer classifiers that report AUROC 0.58-0.77 and species top-1 accuracy of 53.2% on held-out benchmarks.
-
bacpipe: a Python package to make bioacoustic deep learning models accessible
Bacpipe is a modular Python package that integrates state-of-the-art bioacoustic deep learning models to generate embeddings, classifier predictions, and evaluation pipelines for custom audio data.
-
CoarseSoundNet: Building a reliable model for ecological soundscape analysis
The paper introduces CoarseSoundNet, a deep learning model for classifying biophony, geophony, and anthropophony in passive acoustic monitoring recordings, reporting performance gains from additional similar data, a silence class, and decision thresholds, plus a case study on acoustic index trends.