Scarce data, frugal learning

How to learn from scarce data? How to handle underrepresented classes? How to learn from smaller datasets?

Multi-view, multi-task & distributed learning

How to take advantage of multi-view data? How to leverage multi task and distributed learning?

Model-based deep learning

How to go beyond the supervised learning paradigm? Learn with unlabeled or weakly labelled data?

Self-supervised learning

: How to best represent audio data specificities in deep learning models? And improve interpretability?

Learning of (deep) generative models

How to generate new data from interpretable models learnt from few data with good generalization ability?