ORCA-SPY enables killer whale sound source simulation, detection, classification and localization using an integrated deep learning-based segmentation
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...
Published in: | Scientific Reports |
---|---|
Main Authors: | , , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://repository.publisso.de/resource/frl:6482780 https://doi.org/10.1038/s41598-023-38132-7 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10333356/ |
id |
ftzbmed:oai:frl.publisso.de:frl:6482780 |
---|---|
record_format |
openpolar |
spelling |
ftzbmed:oai:frl.publisso.de:frl:6482780 2024-09-15T18:16:41+00:00 ORCA-SPY enables killer whale sound source simulation, detection, classification and localization using an integrated deep learning-based segmentation Hauer, Christopher Nöth, Elmar Barnhill, Alexander Maier, Andreas Guthunz, Julius Hofer, Heribert Cheng, Rachael Xi Barth, Volker Bergler, Christian 2023 https://repository.publisso.de/resource/frl:6482780 https://doi.org/10.1038/s41598-023-38132-7 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10333356/ eng eng https://repository.publisso.de/resource/frl:6482780 https://doi.org/10.1038/s41598-023-38132-7 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10333356/ https://creativecommons.org/licenses/by/4.0/ http://lobid.org/resources/99370675375106441#!, 13(1):11106 Deep Learning [MeSH] Software [MeSH] Computer Simulation [MeSH] Animals [MeSH] Sound [MeSH] Whale Killer [MeSH] Zeitschriftenartikel 2023 ftzbmed https://doi.org/10.1038/s41598-023-38132-7 2024-06-25T14:20:37Z 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 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 dB to 3 dB, a detection rate of 94.0 % was achieved with an average localization error of 7.01. ORCA-SPY was field-tested on Lake Stechlin in Brandenburg Germany 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 during the DeepAL fieldwork 2022 expedition (DLFW22) in Northern ... Article in Journal/Newspaper Killer Whale Orca Orcinus orca Killer whale PUBLISSO Fachrepositorium Lebenswissenschaften (ZB MED) Scientific Reports 13 1 |
institution |
Open Polar |
collection |
PUBLISSO Fachrepositorium Lebenswissenschaften (ZB MED) |
op_collection_id |
ftzbmed |
language |
English |
topic |
Deep Learning [MeSH] Software [MeSH] Computer Simulation [MeSH] Animals [MeSH] Sound [MeSH] Whale Killer [MeSH] |
spellingShingle |
Deep Learning [MeSH] Software [MeSH] Computer Simulation [MeSH] Animals [MeSH] Sound [MeSH] Whale Killer [MeSH] Hauer, Christopher Nöth, Elmar Barnhill, Alexander Maier, Andreas Guthunz, Julius Hofer, Heribert Cheng, Rachael Xi Barth, Volker Bergler, Christian ORCA-SPY enables killer whale sound source simulation, detection, classification and localization using an integrated deep learning-based segmentation |
topic_facet |
Deep Learning [MeSH] Software [MeSH] Computer Simulation [MeSH] Animals [MeSH] Sound [MeSH] Whale Killer [MeSH] |
description |
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 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 dB to 3 dB, a detection rate of 94.0 % was achieved with an average localization error of 7.01. ORCA-SPY was field-tested on Lake Stechlin in Brandenburg Germany 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 during the DeepAL fieldwork 2022 expedition (DLFW22) in Northern ... |
format |
Article in Journal/Newspaper |
author |
Hauer, Christopher Nöth, Elmar Barnhill, Alexander Maier, Andreas Guthunz, Julius Hofer, Heribert Cheng, Rachael Xi Barth, Volker Bergler, Christian |
author_facet |
Hauer, Christopher Nöth, Elmar Barnhill, Alexander Maier, Andreas Guthunz, Julius Hofer, Heribert Cheng, Rachael Xi Barth, Volker Bergler, Christian |
author_sort |
Hauer, Christopher |
title |
ORCA-SPY enables killer whale sound source simulation, detection, classification and localization using an integrated deep learning-based segmentation |
title_short |
ORCA-SPY enables killer whale sound source simulation, detection, classification and localization using an integrated deep learning-based segmentation |
title_full |
ORCA-SPY enables killer whale sound source simulation, detection, classification and localization using an integrated deep learning-based segmentation |
title_fullStr |
ORCA-SPY enables killer whale sound source simulation, detection, classification and localization using an integrated deep learning-based segmentation |
title_full_unstemmed |
ORCA-SPY enables killer whale sound source simulation, detection, classification and localization using an integrated deep learning-based segmentation |
title_sort |
orca-spy enables killer whale sound source simulation, detection, classification and localization using an integrated deep learning-based segmentation |
publishDate |
2023 |
url |
https://repository.publisso.de/resource/frl:6482780 https://doi.org/10.1038/s41598-023-38132-7 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10333356/ |
genre |
Killer Whale Orca Orcinus orca Killer whale |
genre_facet |
Killer Whale Orca Orcinus orca Killer whale |
op_source |
http://lobid.org/resources/99370675375106441#!, 13(1):11106 |
op_relation |
https://repository.publisso.de/resource/frl:6482780 https://doi.org/10.1038/s41598-023-38132-7 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10333356/ |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.1038/s41598-023-38132-7 |
container_title |
Scientific Reports |
container_volume |
13 |
container_issue |
1 |
_version_ |
1810454695618019328 |