Audiocarnet - Deep Representation Learning from Unlabeled Bioacoustic Data
Résumé
Contrastive learning requires creating distinct views of the same input while preserving important details. Standard audio augmentations, such as random resized crops, can remove species-specific characteristics. We propose mixing vocalizations as a domain-agnostic data augmentation, which preserves the unique features of the species of interest while forming a distinct view. This simple strategy allows contrastive learning to capture species-specific features in bird vocalizations from unlabeled data.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |