Global birdsong embeddings enable superior transfer learning for bioacoustic classification

Automated bioacoustic analysis aids understanding and protection of both marine and terrestrial animals and their habitats across extensive spatiotemporal scales, and typically involves analyzing vast collections of acoustic data. With the advent of deep learning models, classifcation of important signals from these datasets has markedly improved. These models power critical data analyses for research and decision-making in biodiversity monitoring, animal behaviour studies, and natural resource management. However, deep learning models are often data-hungry and require a signifcant amount of labeled training data to perform well. While sufcient training data is available for certain taxonomic groups (e.g., common bird species), many classes (such as rare and endangered species, many non-bird taxa, and call-type) lack enough data to train a robust model from scratch. This study investigates the utility of feature embeddings extracted from audio classifcation models to identify bioacoustic classes other than the ones these models were originally trained on. We evaluate models on diverse datasets, including diferent bird calls and dialect types, bat calls, marine mammals calls, and amphibians calls. The embeddings extracted from the models trained on bird vocalization data consistently allowed higher quality classifcation than the embeddings trained on general audio datasets. The results of this study indicate that high-quality feature embeddings from large-scale acoustic bird classifers can be harnessed for few-shot transfer learning, enabling the learning of new classes from a limited quantity of training data. Our fndings reveal the potential for efcient analyses of novel bioacoustic tasks, even in scenarios where available training data is limited to a few samples.

• View at Publisher

Free Full Text ( Final Version , 1mb )