Advancing Marine Bioacoustics With Deep Generative Models: A Hybrid Augmentation Strategy for Southern Resident Killer Whale Detection
Marine Mammal Science · 2026-07 · 42 (3)
DOI: 10.1111/mms.70186 ↗Kurz gefasst
Fachartikel in der Zeitschrift Marine Mammal Science, online erschienen am 05.05.2026. Verfasst von Bruno Padovese und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 93 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Fisheries and Oceans Canada.
Abstract (Originalsprache)
Automated detection and classification of marine mammal vocalizations is critical for conservation and management efforts but is hindered by limited annotated datasets and the acoustic complexity of real‐world marine environments. Data augmentation has proven to be an effective strategy to address this limitation by increasing dataset diversity and improving model generalization without requiring additional field data. However, most augmentation techniques used to date rely on effective but relatively simple transformations, leaving open the question of whether deep generative models can provide additional benefits. In this study, we evaluate the potential of deep generative models for data augmentation in marine mammal call detection including: Variational autoencoders, generative adversarial networks, and denoising diffusion probabilistic models. Using Southern Resident Killer Whale ( Orcinus orca ) vocalizations from two long‐term hydrophone deployments in the Salish Sea, we compare these approaches against traditional augmentation methods such as time‐shifting and vocalization masking. While all generative approaches improved classification performance relative to the baseline, diffusion‐based augmentation yielded the highest recall (0.87) and overall F 1‐score (0.75). A hybrid strategy combining generative‐based synthesis with traditional methods achieved the best overall performance with an F 1‐score of 0.81. We hope this study encourages further exploration of deep generative models as complementary augmentation strategies to advance acoustic monitoring of threatened marine mammal populations.
Förderung
- Fisheries and Oceans Canada
Zitieren
APA
Padovese, B., Frazao, F., Dowd, M., & Joy, R. (2026). Advancing Marine Bioacoustics With Deep Generative Models: A Hybrid Augmentation Strategy for Southern Resident Killer Whale Detection. Marine Mammal Science, 42(3). https://doi.org/10.1111/mms.70186
Vancouver
Padovese B, Frazao F, Dowd M, Joy R. Advancing Marine Bioacoustics With Deep Generative Models: A Hybrid Augmentation Strategy for Southern Resident Killer Whale Detection. Marine Mammal Science. 2026;42(3). doi:10.1111/mms.70186
BibTeX
@article{Padovese2026,
author = {Padovese, Bruno and Frazao, Fabio and Dowd, Michael and Joy, Ruth},
title = {Advancing Marine Bioacoustics With Deep Generative Models: A Hybrid Augmentation Strategy for Southern Resident Killer Whale Detection},
journal = {Marine Mammal Science},
year = {2026},
volume = {42},
number = {3},
doi = {10.1111/mms.70186}
}
EUVIMED