Intelligent identification of dolphin whistle in acoustic signals via deep learning
- 1Department of Information Engineering, Università Politecnica delle Marche
- 2Institute of Biological Resources and Marine Biotechnology (IRBIM), National Research Council (CNR)
Abstract
Deep learning has been increasingly employed for identifying dolphin vocalizations. Specifically, convolutional neural networks (CNNs) proved effective in detecting dolphin whistles. The aim of the study is to introduce a novel method based on CNNs and Sobel filter to identify dolphin whistles from spectrograms extracted from underwater audio recordings. Moreover, sensitivity analysis was performed to investigate the impact of Sobel filter compared with other filtering approaches (CLAHE and Laplacian), spectrogram size, and CNN kernel shape on model performance. Three independent datasets of bottlenose dolphin vocalizations were used, recorded (1) in a dolphin pool of Oltremare marine park; (2) in the Adriatic Sea during interactions between dolphins and fishing activities; and (3) in open-sea conditions in the Hawaiian Exclusive Economic Zone (DCLDE 2022). Results showed that, in the best-case scenario, model accuracy and F1-score were 90.0% and the vertical Sobel filter significantly improved CNN performance compared with unfiltered spectrograms and with CLAHE and Laplacian filtering. Rectangular spectrograms also enhanced performance over square spectrograms. Instead, variation in CNN kernel shape had minimal impact. Model effectiveness was preserved even under challenging conditions of depredation in open sea. Moreover, computation time is compatible with real-time applications. Model suitability in different environments and the low computational time make this approach appropriate for monitoring underwater environments.
Related
- Preliminary insights into the acoustic presence and diel patterns of odontocetes in French Polynesia from whistle detections
- An embedded deep learning–fuzzy logic framework for intelligent and automated irrigation in smart farming
- AVISNet: An edge-computing model for acoustic identification of species from the Doñana bird community
- Recording context and data splitting can inflate acoustic re-identification accuracy across species and studies
- Composite learning based finite time nonsingular terminal sliding mode path tracking control for intelligent vehicles
BibTeX
@article{scaradozzi2026intelligent,
title = {{Intelligent identification of dolphin whistle in acoustic signals via deep learning}},
author = {David Scaradozzi and Rocco De Marco and Laura Screpanti and Francesco Di Nardo},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-61901-z},
url = {https://doi.org/10.1038/s41598-026-61901-z},
note = {CC BY},
}
RIS
TY - JOUR
TI - Intelligent identification of dolphin whistle in acoustic signals via deep learning
AU - David Scaradozzi
AU - Rocco De Marco
AU - Laura Screpanti
AU - Francesco Di Nardo
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-61901-z
UR - https://doi.org/10.1038/s41598-026-61901-z
AB - Deep learning has been increasingly employed for identifying dolphin vocalizations. Specifically, convolutional neural networks (CNNs) proved effective in detecting dolphin whistles. The aim of the study is to introduce a novel method based on CNNs and Sobel filter to identify dolphin whistles from spectrograms extracted from underwater audio recordings. Moreover, sensitivity analysis was performed to investigate the impact of Sobel filter compared with other filtering approaches (CLAHE and Laplacian), spectrogram size, and CNN kernel shape on model performance. Three independent datasets of bottlenose dolphin vocalizations were used, recorded (1) in a dolphin pool of Oltremare marine park; (2) in the Adriatic Sea during interactions between dolphins and fishing activities; and (3) in open-sea conditions in the Hawaiian Exclusive Economic Zone (DCLDE 2022). Results showed that, in the best-case scenario, model accuracy and F1-score were 90.0% and the vertical Sobel filter significantly improved CNN performance compared with unfiltered spectrograms and with CLAHE and Laplacian filtering. Rectangular spectrograms also enhanced performance over square spectrograms. Instead, variation in CNN kernel shape had minimal impact. Model effectiveness was preserved even under challenging conditions of depredation in open sea. Moreover, computation time is compatible with real-time applications. Model suitability in different environments and the low computational time make this approach appropriate for monitoring underwater environments.
SN - 2045-2322
ER -