Published several papers on the application of machine listening in bioacoustics, including 'From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learning' (2024 European Signal Processing Conference) and 'The Accuracy Cost of Weakness: A Theoretical Analysis of Fixed-Segment Weak Labeling for Events in Time' (Transactions on Machine Learning Research).
Research Experience
Involved in the AukLab-Audio project, collaborating with Jonas Hentati Sundberg, Delia Fano Yela, and Olof Mogren on acoustic monitoring of seabirds in the Baltic Sea. Collaborated with Tuomas Virtanen from Tampere University during a research visit at the Audio Research Group.
Education
PhD student at RISE, affiliated with Lund University. Supervisors are Olof Mogren and Maria Sandsten. Also a core member of Climate AI Nordics.
Background
Passionate about machine listening, focusing on bioacoustics and biodiversity monitoring. Aims to develop robust models that perform well with limited labeled data and improve the efficiency and accuracy of bioacoustic data labeling.
Miscellany
Interested in automating the sensing and monitoring of natural environments, particularly for tracking animal populations, through machine listening technologies.