MetaPerch: Learning from metadata for bioacoustics foundation models
2026-07-15 • Machine Learning
Machine LearningSound
AI summaryⓘ
The authors studied how adding extra information like location and time from bird sound recordings can help models identify species better. They found that using this kind of metadata along with the sounds helps the model learn stronger patterns and work well even when conditions change. Their new model, MetaPerch, performed well on many tough datasets by using these additional clues. This approach could improve how we track species in the wild using sound recordings.
bioacousticsfoundation modelsspecies identificationmetadatapassive acoustic monitoringsupervised learningXeno-Cantorepresentation learningdistribution shift
Authors
Mustafa Chasmai, Vincent Dumoulin, Jenny Hamer
Abstract
Bioacoustic foundation models rely on large-scale citizen science platforms like Xeno-Canto for geographically and ecologically diverse data. Recent work has shown that supervision alone can produce SotA species detection models when trained on this large-scale data -- however, there remains unutilized potential in the form of recording metadata readily available within these community-driven data hubs. In this work, we explore the use of metadata -- such as location and time -- as auxiliary supervision signals, allowing the model to leverage species-metadata correlations in its learned representation. Auxiliary metadata losses provide additional information beyond vocalizations alone that can encourage a richer, more robust representation that generalizes better to species distribution and acoustic domain shifts -- important challenges for deployment in real-world passive acoustic monitoring (PAM) settings. We introduce MetaPerch, a new foundation model that achieves strong species identification performance across multiple challenging domains and present an extensive empirical study of the effects of 9 diverse metadata sources on 17 bioacoustic datasets.