Personal profile
Research
Read about my research, publications, and blog posts on my personal webpage.
My research focuses on developing machine learning methods to enable efficient and accurate monitoring of natural environments through sound. I specialize in annotation-efficient techniques for bioacoustics and ecoacoustics, improving how we label and analyze audio data to detect species and estimate biodiversity with less human supervision. I develop tools that help us get a more comprehensive understanding of our ecosystems, to monitor the impacts of human activities and inform policies for biodiversity conservation.
Free keywords
- Machine learning
- Machine listening
- Bioacoustics
- Annotation
- Biodiversity
Expertise related to UN Sustainable Development Goals
In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This person’s work contributes towards the following SDG(s):
-
SDG 14 Life Below Water -
SDG 15 Life on Land
Fingerprint
- 1 Similar Profiles
Collaborations the last five years
-
The Accuracy Cost of Weakness: A Theoretical Analysis of Fixed-Segment Weak Labeling for Events in Time
Martinsson, J., Virtanen, T., Sandsten, M. & Mogren, O., 2025, In: Transactions on Machine Learning Research. 2025-SeptemberResearch output: Contribution to journal › Article › peer-review
-
Efficient and precise annotation of local structures in data
Martinsson, J., 2024 Oct 3, Lund: Centre for Mathematical Sciences, Lund University. 120 p.Research output: Thesis › Licentiate Thesis
Open AccessFile77 Downloads (Pure) -
From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learning
Martinsson, J., Mogren, O., Sandsten, M. & Virtanen, T., 2024 Aug 30, 32nd European Signal Processing Conference (EUSIPCO), proceedings of. p. 902-906Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review
Open Access -
DMEL: THE DIFFERENTIABLE LOG-MEL SPECTROGRAM AS A TRAINABLE LAYER IN NEURAL NETWORKS
Martinsson, J. & Sandsten, M., 2024, 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings. IEEE - Institute of Electrical and Electronics Engineers Inc., p. 5005-5009 5 p. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review
-
Few-Shot Bioacoustic Event Detection Using an Event-Length Adapted Ensemble of Prototypical Networks
Martinsson, J., Sandsten, M., Willbo, M., Pirinen, A. & Mogren, O., 2022, Proceedings of the 7th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2022). 5 p.Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review
Open Access