Acoustic recognition of individuals in closed and open bird populations

Passive acoustic monitoring is firmly established as an effective non-invasive technique for wildlife monitoring. The analysis of animal vocalisations recorded in their natural habitats is commonly used to monitor species occupancy, distribution mapping and community composition. However, the ability to distinguish between individual animals by their vocalisations remains underexplored and presents an exciting opportunity to study individual animal behaviour and population demographics in more detail. In this work, we investigate bioacoustic individual-level recognition. We extend on the predominant focus of existing work, where all individuals are known a priori, and additionally address situations where only a subset of the population is initially known and labelled. This is crucial because wildlife populations are constantly changing so that solutions operating only within a known set of individuals are not realistically applicable in the wild. Using two novel datasets, we show that models initially trained to classify only known individuals can also be extended to detect new and previously unknown individuals not included in the training set. We demonstrate that feature extractors pretrained on species classification can be successfully adapted for this task. Extending individual-level recognition to unknown individuals, so-called out-of-distribution classification, is a crucial step towards making individual recognition a realistic possibility in the wild.