Creating Generalizable Data-Driven Approaches for Biodiversity Monitoring via Acoustics

Global biodiversity is declining at unprecedented rates, yet traditional monitoring at the necessary scales remains costly and biased toward what can be seen. Sound offers a complementary lens: many species are detected more reliably by their vocalizations, microphones are inexpensive and unobtrusive, and they can cover greater spatial and temporal scales. These advantages have made passive acoustic monitoring a fast-growing paradigm, yet robust, generalizable sound distinction in complex soundscapes remain a central obstacle. My thesis addresses this by combining data-driven human-inspired representation learning with knowledge-guided unsupervised learning from auditory scene analysis and ecological reasoning, prioritizing hierarchical organization and structure discovery prior to labelling. Human-in-the-loop oversight is incorporated as targeted verification under uncertainty, drawing on active learning and weak supervision to direct effort where it has the highest value.