Silbido profundo : an open source package for the use of deep learning to detect odontocete whistles
Funding: The authors wish to thank Dr. Michael Weise of the Office of Naval Research (N00014-17-1-2867, N00014-17-1-2567) for supporting this project. We also thank Anu Kumar and Mandy Shoemaker of U.S. Navy Living Marine Resources for supporting development of the data management tools used in this...
Published in: | The Journal of the Acoustical Society of America |
---|---|
Main Authors: | , , , , , , , |
Other Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | http://hdl.handle.net/10023/26799 https://doi.org/10.1121/10.0016631 |
id |
ftstandrewserep:oai:research-repository.st-andrews.ac.uk:10023/26799 |
---|---|
record_format |
openpolar |
spelling |
ftstandrewserep:oai:research-repository.st-andrews.ac.uk:10023/26799 2024-02-11T10:09:09+01:00 Silbido profundo : an open source package for the use of deep learning to detect odontocete whistles Conant, Peter C. Li, Pu Liu, Xiaobai Klinck, Holger Fleishman, Erica Gillespie, Douglas Nosal, Eva-Marie Roch, Marie A. University of St Andrews. School of Biology University of St Andrews. Sea Mammal Research Unit University of St Andrews. Scottish Oceans Institute University of St Andrews. Sound Tags Group University of St Andrews. Bioacoustics group University of St Andrews. Marine Alliance for Science & Technology Scotland 2023-01-20T15:30:10Z 9 application/pdf http://hdl.handle.net/10023/26799 https://doi.org/10.1121/10.0016631 eng eng Journal of the Acoustical Society of America Conant , P C , Li , P , Liu , X , Klinck , H , Fleishman , E , Gillespie , D , Nosal , E-M & Roch , M A 2022 , ' Silbido profundo : an open source package for the use of deep learning to detect odontocete whistles ' , Journal of the Acoustical Society of America , vol. 152 , no. 6 , pp. 3800-3808 . https://doi.org/10.1121/10.0016631 0001-4966 PURE: 283033038 PURE UUID: de0d03ea-698f-4aa3-8a87-3858658c1220 Jisc: 826488 Scopus: 85145425255 ORCID: /0000-0001-9628-157X/work/127066286 WOS: 000904650700002 http://hdl.handle.net/10023/26799 https://doi.org/10.1121/10.0016631 Copyright © 2022 Author(s). All article content, except where otherwise noted, is licensed under a Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). Acoustics and ultrasonics DAS MCC Journal article 2023 ftstandrewserep https://doi.org/10.1121/10.0016631 2024-01-25T23:29:29Z Funding: The authors wish to thank Dr. Michael Weise of the Office of Naval Research (N00014-17-1-2867, N00014-17-1-2567) for supporting this project. We also thank Anu Kumar and Mandy Shoemaker of U.S. Navy Living Marine Resources for supporting development of the data management tools used in this work (N3943020C2202). This work presents an open-source matlab software package for exploiting recent advances in extracting tonal signals from large acoustic data sets. A whistle extraction algorithm published by Li, Liu, Palmer, Fleishman, Gillespie, Nosal, Shiu, Klinck, Cholewiak, Helble, and Roch [(2020). Proceedings of the International Joint Conference on Neural Networks, July 19–24, Glasgow, Scotland, p. 10] is incorporated into silbido, an established software package for extraction of cetacean tonal calls. The precision and recall of the new system were over 96% and nearly 80%, respectively, when applied to a whistle extraction task on a challenging two-species subset of a conference-benchmark data set. A second data set was examined to assess whether the algorithm generalized to data that were collected across different recording devices and locations. These data included 487 h of weakly labeled, towed array data collected in the Pacific Ocean on two National Oceanographic and Atmospheric Administration (NOAA) cruises. Labels for these data consisted of regions of toothed whale presence for at least 15 species that were based on visual and acoustic observations and not limited to whistles. Although the lack of per whistle-level annotations prevented measurement of precision and recall, there was strong concurrence of automatic detections and the NOAA annotations, suggesting that the algorithm generalizes well to new data. Publisher PDF Peer reviewed Article in Journal/Newspaper toothed whale University of St Andrews: Digital Research Repository Pacific Silbido ENVELOPE(-67.593,-67.593,-67.497,-67.497) The Journal of the Acoustical Society of America 152 6 3800 3808 |
institution |
Open Polar |
collection |
University of St Andrews: Digital Research Repository |
op_collection_id |
ftstandrewserep |
language |
English |
topic |
Acoustics and ultrasonics DAS MCC |
spellingShingle |
Acoustics and ultrasonics DAS MCC Conant, Peter C. Li, Pu Liu, Xiaobai Klinck, Holger Fleishman, Erica Gillespie, Douglas Nosal, Eva-Marie Roch, Marie A. Silbido profundo : an open source package for the use of deep learning to detect odontocete whistles |
topic_facet |
Acoustics and ultrasonics DAS MCC |
description |
Funding: The authors wish to thank Dr. Michael Weise of the Office of Naval Research (N00014-17-1-2867, N00014-17-1-2567) for supporting this project. We also thank Anu Kumar and Mandy Shoemaker of U.S. Navy Living Marine Resources for supporting development of the data management tools used in this work (N3943020C2202). This work presents an open-source matlab software package for exploiting recent advances in extracting tonal signals from large acoustic data sets. A whistle extraction algorithm published by Li, Liu, Palmer, Fleishman, Gillespie, Nosal, Shiu, Klinck, Cholewiak, Helble, and Roch [(2020). Proceedings of the International Joint Conference on Neural Networks, July 19–24, Glasgow, Scotland, p. 10] is incorporated into silbido, an established software package for extraction of cetacean tonal calls. The precision and recall of the new system were over 96% and nearly 80%, respectively, when applied to a whistle extraction task on a challenging two-species subset of a conference-benchmark data set. A second data set was examined to assess whether the algorithm generalized to data that were collected across different recording devices and locations. These data included 487 h of weakly labeled, towed array data collected in the Pacific Ocean on two National Oceanographic and Atmospheric Administration (NOAA) cruises. Labels for these data consisted of regions of toothed whale presence for at least 15 species that were based on visual and acoustic observations and not limited to whistles. Although the lack of per whistle-level annotations prevented measurement of precision and recall, there was strong concurrence of automatic detections and the NOAA annotations, suggesting that the algorithm generalizes well to new data. Publisher PDF Peer reviewed |
author2 |
University of St Andrews. School of Biology University of St Andrews. Sea Mammal Research Unit University of St Andrews. Scottish Oceans Institute University of St Andrews. Sound Tags Group University of St Andrews. Bioacoustics group University of St Andrews. Marine Alliance for Science & Technology Scotland |
format |
Article in Journal/Newspaper |
author |
Conant, Peter C. Li, Pu Liu, Xiaobai Klinck, Holger Fleishman, Erica Gillespie, Douglas Nosal, Eva-Marie Roch, Marie A. |
author_facet |
Conant, Peter C. Li, Pu Liu, Xiaobai Klinck, Holger Fleishman, Erica Gillespie, Douglas Nosal, Eva-Marie Roch, Marie A. |
author_sort |
Conant, Peter C. |
title |
Silbido profundo : an open source package for the use of deep learning to detect odontocete whistles |
title_short |
Silbido profundo : an open source package for the use of deep learning to detect odontocete whistles |
title_full |
Silbido profundo : an open source package for the use of deep learning to detect odontocete whistles |
title_fullStr |
Silbido profundo : an open source package for the use of deep learning to detect odontocete whistles |
title_full_unstemmed |
Silbido profundo : an open source package for the use of deep learning to detect odontocete whistles |
title_sort |
silbido profundo : an open source package for the use of deep learning to detect odontocete whistles |
publishDate |
2023 |
url |
http://hdl.handle.net/10023/26799 https://doi.org/10.1121/10.0016631 |
long_lat |
ENVELOPE(-67.593,-67.593,-67.497,-67.497) |
geographic |
Pacific Silbido |
geographic_facet |
Pacific Silbido |
genre |
toothed whale |
genre_facet |
toothed whale |
op_relation |
Journal of the Acoustical Society of America Conant , P C , Li , P , Liu , X , Klinck , H , Fleishman , E , Gillespie , D , Nosal , E-M & Roch , M A 2022 , ' Silbido profundo : an open source package for the use of deep learning to detect odontocete whistles ' , Journal of the Acoustical Society of America , vol. 152 , no. 6 , pp. 3800-3808 . https://doi.org/10.1121/10.0016631 0001-4966 PURE: 283033038 PURE UUID: de0d03ea-698f-4aa3-8a87-3858658c1220 Jisc: 826488 Scopus: 85145425255 ORCID: /0000-0001-9628-157X/work/127066286 WOS: 000904650700002 http://hdl.handle.net/10023/26799 https://doi.org/10.1121/10.0016631 |
op_rights |
Copyright © 2022 Author(s). All article content, except where otherwise noted, is licensed under a Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
op_doi |
https://doi.org/10.1121/10.0016631 |
container_title |
The Journal of the Acoustical Society of America |
container_volume |
152 |
container_issue |
6 |
container_start_page |
3800 |
op_container_end_page |
3808 |
_version_ |
1790608912330784768 |