Supplementary material from "Improve automatic detection of animal call sequences with temporal context"
Many animals rely on long-form communication, in the form of songs, for vital functions such as mate attraction and territorial defence. We explored the prospect of improving automatic recognition performance by using the temporal context inherent in song. The ability to accurately detect sequences...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
The Royal Society
2021
|
Subjects: | |
Online Access: | https://dx.doi.org/10.6084/m9.figshare.c.5492899.v1 https://rs.figshare.com/collections/Supplementary_material_from_Improve_automatic_detection_of_animal_call_sequences_with_temporal_context_/5492899/1 |
id |
ftdatacite:10.6084/m9.figshare.c.5492899.v1 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.6084/m9.figshare.c.5492899.v1 2023-05-15T15:36:38+02:00 Supplementary material from "Improve automatic detection of animal call sequences with temporal context" Madhusudhana, Shyam Shiu, Yu Klinck, Holger Fleishman, Erica Liu, Xiaobai Nosal, Eva-Marie Helble, Tyler Cholewiak, Danielle Gillespie, Douglas Širović, Ana Roch, Marie A. 2021 https://dx.doi.org/10.6084/m9.figshare.c.5492899.v1 https://rs.figshare.com/collections/Supplementary_material_from_Improve_automatic_detection_of_animal_call_sequences_with_temporal_context_/5492899/1 unknown The Royal Society https://dx.doi.org/10.1098/rsif.2021.0297 https://dx.doi.org/10.6084/m9.figshare.c.5492899 Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 CC-BY Environmental Science Computational Biology Collection article 2021 ftdatacite https://doi.org/10.6084/m9.figshare.c.5492899.v1 https://doi.org/10.1098/rsif.2021.0297 https://doi.org/10.6084/m9.figshare.c.5492899 2021-11-05T12:55:41Z Many animals rely on long-form communication, in the form of songs, for vital functions such as mate attraction and territorial defence. We explored the prospect of improving automatic recognition performance by using the temporal context inherent in song. The ability to accurately detect sequences of calls has implications for conservation and biological studies. We show that the performance of a convolutional neural network (CNN), designed to detect song notes (calls) in short-duration audio segments, can be improved by combining it with a recurrent network designed to process sequences of learned representations from the CNN on a longer time scale. The combined system of independently trained CNN and long short-term memory (LSTM) network models exploits the temporal patterns between song notes. We demonstrate the technique using recordings of fin whale ( Balaenoptera physalus ) songs, which comprise patterned sequences of characteristic notes. We evaluated several variants of the CNN + LSTM network. Relative to the baseline CNN model, the CNN + LSTM models reduced performance variance, offering 9–17% increase in area under the precision–recall curve and 9–18% increase in peak F1-scores. These results show that the inclusion of temporal information may offer a valuable pathway for improving the automatic recognition and transcription of wildlife recordings. Article in Journal/Newspaper Balaenoptera physalus Fin whale DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Environmental Science Computational Biology |
spellingShingle |
Environmental Science Computational Biology Madhusudhana, Shyam Shiu, Yu Klinck, Holger Fleishman, Erica Liu, Xiaobai Nosal, Eva-Marie Helble, Tyler Cholewiak, Danielle Gillespie, Douglas Širović, Ana Roch, Marie A. Supplementary material from "Improve automatic detection of animal call sequences with temporal context" |
topic_facet |
Environmental Science Computational Biology |
description |
Many animals rely on long-form communication, in the form of songs, for vital functions such as mate attraction and territorial defence. We explored the prospect of improving automatic recognition performance by using the temporal context inherent in song. The ability to accurately detect sequences of calls has implications for conservation and biological studies. We show that the performance of a convolutional neural network (CNN), designed to detect song notes (calls) in short-duration audio segments, can be improved by combining it with a recurrent network designed to process sequences of learned representations from the CNN on a longer time scale. The combined system of independently trained CNN and long short-term memory (LSTM) network models exploits the temporal patterns between song notes. We demonstrate the technique using recordings of fin whale ( Balaenoptera physalus ) songs, which comprise patterned sequences of characteristic notes. We evaluated several variants of the CNN + LSTM network. Relative to the baseline CNN model, the CNN + LSTM models reduced performance variance, offering 9–17% increase in area under the precision–recall curve and 9–18% increase in peak F1-scores. These results show that the inclusion of temporal information may offer a valuable pathway for improving the automatic recognition and transcription of wildlife recordings. |
format |
Article in Journal/Newspaper |
author |
Madhusudhana, Shyam Shiu, Yu Klinck, Holger Fleishman, Erica Liu, Xiaobai Nosal, Eva-Marie Helble, Tyler Cholewiak, Danielle Gillespie, Douglas Širović, Ana Roch, Marie A. |
author_facet |
Madhusudhana, Shyam Shiu, Yu Klinck, Holger Fleishman, Erica Liu, Xiaobai Nosal, Eva-Marie Helble, Tyler Cholewiak, Danielle Gillespie, Douglas Širović, Ana Roch, Marie A. |
author_sort |
Madhusudhana, Shyam |
title |
Supplementary material from "Improve automatic detection of animal call sequences with temporal context" |
title_short |
Supplementary material from "Improve automatic detection of animal call sequences with temporal context" |
title_full |
Supplementary material from "Improve automatic detection of animal call sequences with temporal context" |
title_fullStr |
Supplementary material from "Improve automatic detection of animal call sequences with temporal context" |
title_full_unstemmed |
Supplementary material from "Improve automatic detection of animal call sequences with temporal context" |
title_sort |
supplementary material from "improve automatic detection of animal call sequences with temporal context" |
publisher |
The Royal Society |
publishDate |
2021 |
url |
https://dx.doi.org/10.6084/m9.figshare.c.5492899.v1 https://rs.figshare.com/collections/Supplementary_material_from_Improve_automatic_detection_of_animal_call_sequences_with_temporal_context_/5492899/1 |
genre |
Balaenoptera physalus Fin whale |
genre_facet |
Balaenoptera physalus Fin whale |
op_relation |
https://dx.doi.org/10.1098/rsif.2021.0297 https://dx.doi.org/10.6084/m9.figshare.c.5492899 |
op_rights |
Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.6084/m9.figshare.c.5492899.v1 https://doi.org/10.1098/rsif.2021.0297 https://doi.org/10.6084/m9.figshare.c.5492899 |
_version_ |
1766367009042333696 |