Audio and Speech Processing

Incremental learning for audio classification with Hebbian Deep Neural Networks

This paper applies Hebbian learning principles to audio classification in a continual learning setting, introducing a kernel plasticity approach that selectively updates network weights to balance learning new sounds while retaining knowledge of previously learned ones. On the ESC-50 dataset, the method achieves 76.3% accuracy across five incremental learning steps, significantly outperforming a baseline approach.