Clustering humpback whale calls using deep feature embeddings and latent representations
The Journal of the Acoustical Society of America · 01.10.2025 · 158 (4_Supplement) · A274-A274
DOI: 10.1121/10.0040864 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, erschienen am 01.10.2025. Verfasst von Elizabeth L. Ferguson und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Understanding the structure and variability of animal acoustic repertoires is essential for studying communication and behavior. In this project, we investigated unsupervised deep learning approaches to cluster humpback whale social calls collected from Morro Bay (California), Monterey Bay (California), and Newport (Oregon). Over 6000 calls were manually annotated into 12 broad categories based on call structure observed in spectrograms. Using the DeepAcoustics tool, we applied two distinct deep learning strategies—VisualGeometry Group (VGG) and Variational Autoencoders (VAEs)—to cluster the bounding-box annotated calls. These approaches differ in how they interpret and represent input data: VGG applies a hierarchical convolutional structure to extract fixed visual features from images, while VAEs use an encoder–decoder architecture to learn compressed, lower-dimensional representations that capture variation in the input data, allowing for grouping of similar patterns and identification of outliers. We evaluated how well each method captured structural variation among call types and examined the influence of recording artifacts and background noise on clustering performance. We share important trade-offs between model type, sensitivity to noise, and ability to distinguish nuanced call features. We also discuss the potential benefits of using deep learning architectures developed for raw audio formats to improve clustering of data.
Zitieren
APA
Ferguson, E. L., & Alongi, G. C. (2025). Clustering humpback whale calls using deep feature embeddings and latent representations. The Journal of the Acoustical Society of America, 158(4_Supplement), A274-A274. https://doi.org/10.1121/10.0040864
Vancouver
Ferguson EL, Alongi GC. Clustering humpback whale calls using deep feature embeddings and latent representations. The Journal of the Acoustical Society of America. 2025;158(4_Supplement):A274-A274. doi:10.1121/10.0040864
BibTeX
@article{Ferguson2025,
author = {Ferguson, Elizabeth L. and Alongi, Gabriela C.},
title = {Clustering humpback whale calls using deep feature embeddings and latent representations},
journal = {The Journal of the Acoustical Society of America},
year = {2025},
volume = {158},
number = {4_Supplement},
pages = {A274--A274},
doi = {10.1121/10.0040864}
}
EUVIMED