Lukas builds deep learning models for animal sound. During his PhD he created BirdSet, a benchmark now widely used in avian bioacoustics. His research covers self-supervised learning for audio representations as well as interpretability, so that models can be understood rather than treated as black boxes. His broader aim is to establish bioacoustics as a frontier domain for deep learning while turning state-of-the-art methods into practical tools for conservation and monitoring.
Lukas Rauch
Postdoctoral Researcher