Automated detection and annotation of toothed-whale whistles using transformer-based instance segmentation
The Journal of the Acoustical Society of America · 01.06.2026 · 159 (6) · 5693-5706
DOI: 10.1121/10.0044187 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 24.06.2026. Verfasst von Xixin Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, San Diego State University, San Diego, California 92182, USA. Hauptthemen laut MEDLINE: Vocalization, Animal, Signal Processing, Computer-Assisted, Echolocation, Acoustics. Die Arbeit nennt 56 Literaturangaben. Gefördert von: Office of Naval Research.
Abstract (Originalsprache)
Accurate detection and fine-scale annotation of dolphin whistles are crucial for understanding marine mammal communication and population dynamics. Dolphin-whistle annotation is challenging due to highly variable signals, overlapping calls including echolocation clicks, attenuation, and noisy backgrounds. Most existing methods treat the task as a spectrogram peak-tracking problem, linking neighboring detected peaks using heuristic or statistical methods, and rely on manual feature engineering. While effective for long, clear whistles, they lack generalizability for short, weak whistles across species. We reformulated dolphin-whistle detection as an instance-segmentation task, introducing an end-to-end transformer model that predicted complete whistle contours directly from spectrograms, eliminating peak-detection and trajectory-reconstruction stages. To overcome manual labeling limitations, we integrated a human-in-the-loop training paradigm that iteratively refined annotations, improving both data quality and model performance. We demonstrated the effectiveness of this architecture on a subset of the detection, classification, localization, and density estimation 2011 corpus where we partitioned training and test data such that test data were from species, locations, and hydrophones that were excluded from the training data. Experiments showed that our end-to-end system generalized effectively in these conditions, achieving 89.99% precision and 80.65% recall for all whistles, and 85.81% precision with 88.44% recall for whistles longer than 150 ms.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Science, San Diego State University, San Diego, California 92182, USA.
- Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, California 92093, USA.
- Scripps Institution of Oceanography, University of California San Diego, La Jolla, California 92092, USA.
ORCID-Profile: Xixin Zhang, Xiaobai Liu, Michaela N Alksne, Marie A Roch
Förderung
- Office of Naval Research
Zitieren
APA
Zhang, X., Liu, X., Alksne, M. N., & Roch, M. A. (2026). Automated detection and annotation of toothed-whale whistles using transformer-based instance segmentation. The Journal of the Acoustical Society of America, 159(6), 5693-5706. https://doi.org/10.1121/10.0044187
Vancouver
Zhang X, Liu X, Alksne MN, Roch MA. Automated detection and annotation of toothed-whale whistles using transformer-based instance segmentation. The Journal of the Acoustical Society of America. 2026;159(6):5693-5706. doi:10.1121/10.0044187
BibTeX
@article{Zhang2026,
author = {Zhang, Xixin and Liu, Xiaobai and Alksne, Michaela N and Roch, Marie A},
title = {Automated detection and annotation of toothed-whale whistles using transformer-based instance segmentation},
journal = {The Journal of the Acoustical Society of America},
year = {2026},
volume = {159},
number = {6},
pages = {5693--5706},
doi = {10.1121/10.0044187}
}
EUVIMED