Hauer C, Nöth E, Barnhill A, Maier A, Guthunz J, Hofer H, Cheng RX, Barth V, Bergler C (2023)
Publication Language: English
Publication Type: Journal article
Publication year: 2023
Book Volume: UNDER REVIEW
Acoustic identification of vocalizing individuals opens up new and deeper insights into animal communications, such as individual-/group-specific dialects, turn-taking events, and dialogs. However, establishing an association between an individual animal and its emitted signal is usually non-trivial, especially for animals underwater. Consequently, a collection of marine species-, array-, and position-specific ground truth localization data is extremely challenging, which strongly limits possibilities to evaluate localization methods beforehand or at all. This study presents ORCA-SPY, a fully-automated sound source simulation, classification and localization framework for passive killer whale (Orcinus orca) acoustic monitoring that is embedded into PAMGuard, a widely used bioacoustic software toolkit. ORCA-SPY enables array- and position-specific multichannel audio stream generation to simulate real-world ground truth killer whale localization data and provides a hybrid sound source identification approach integrating ANIMAL-SPOT, a state-of-the-art deep learning-based orca detection network, followed by downstream Time-Difference-Of-Arrival (TDOA) localization. ORCA-SPY was evaluated on simulated multichannel underwater audio streams including various killer whale vocalization events within a large-scale experimental setup benefiting from previous real-world fieldwork experience. Across all 58,320 embedded vocalizing killer whale events, subject to various hydrophone array geometries, call types, distances, and noise conditions responsible for a signal-to-noise ratio varying from -14.2dB to 3dB, a detection rate of 94.0 % was achieved with an average localization error of 7.01°. ORCA-SPY was field-tested on the lake Stechlin under laboratory conditions with a focus on localization. During the field test, 3889 localization events were observed with an average error of 29.19° and a median error of 17.54°. ORCA-SPY was deployed successfully at the DeepAL fieldwork 2022 expedition (DLFW22) in Northern British Columbia, with a mean average error of 20.01° and a median error of 11.01° across 503 localization events. ORCA-SPY is an open-source and publicly available software framework, which can be adapted to various recording conditions as well as animal species.
APA:
Hauer, C., Nöth, E., Barnhill, A., Maier, A., Guthunz, J., Hofer, H.,... Bergler, C. (2023). ORCA-SPY: Killer Whale Sound Source Simulation and Detection, Classification and Localization in PAMGuard Utilizing Integrated Deep Learning Based Segmentation. Scientific Reports, UNDER REVIEW.
MLA:
Hauer, Christopher, et al. "ORCA-SPY: Killer Whale Sound Source Simulation and Detection, Classification and Localization in PAMGuard Utilizing Integrated Deep Learning Based Segmentation." Scientific Reports UNDER REVIEW (2023).
BibTeX: Download