“Representation-Diverse Self-Supervision for Cross-Domain Bioacoustic Learning in Low-Resource Settings” was presented at ICASSP 2026.
The paper addresses low-resource bioacoustic learning with self-supervised representations, connecting audio analysis, machine learning and cross-domain generalisation. It is a strong signal-processing and multimedia research highlight linked with Antigoni Tsiami’s profile.
- Authors: Dimitrios N. Makropoulos, Christos Garoufis, Antigoni Tsiami, Panagiotis P. Filntisis, Petros Maragos
- Venue: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2026), Barcelona, Spain
- Presentation date: 6 May 2026
- DOI: 10.1109/ICASSP55912.2026.11461507
- Conference page: ICASSP 2026 listing
You may also like
-
TMLR 2026: prescriptive SVD-inspired attention via spectral energy retention
-
Towards Heritage World Models: from digital twins to predictive heritage systems
-
AISTATS 2026: process-tensor tomography of SGD and training memory
-
ICPRAM 2026: two-stage angular alignment for positive-unlabeled learning
-
IEEE Access 2026: interpretable Vision Transformers via SVDA