Robust acoustic monitoring of wildlife communities

Pre-trained classifiers for bioacoustic species detection have emerged as accessible tools for conservation and automated biodiversity monitoring at scale. Despite their wide use, these models are trained primarily on high quality, weakly labeled species recordings from disparate regions that can fail to account for variation in passive ambient soundscape data due to poor signal-to-noise ratio and the presence of novel sounds such as abiotic noise and concurrent vocalizations. Although relatively underexplored in bioacoustic monitoring, transfer learning may help overcome the limitations of existing pre-trained classifiers by enhancing predictive performance while avoiding the time, resources, and expertise required to develop entirely new models. We demonstrate the use of few-shot transfer learning as a strategy to efficiently adapt a pre-trained BirdNET source model to a new target domain with minimal local training data.

Jacuzzi, G., and J.D. Olden. 2025. Few-shot transfer learning enables robust acoustic monitoring of wildlife communities at the landscape scale. Ecological Informatics 90, 103294.