Learning Deep Models from Synthetic Data for Extracting Dolphin Whistle Contours
We present a learning-based method for extracting whistles of toothed whales (Odontoceti) in hydrophone recordings. Our method represents audio signals as time-frequency spectrograms and decomposes each spectrogram into a set of time-frequency patches. A deep neural network learns archetypical patte...
Published in: | 2020 International Joint Conference on Neural Networks (IJCNN) |
---|---|
Main Authors: | , , , , , , , , , , |
Format: | Other Non-Article Part of Journal/Newspaper |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers Inc.
2020
|
Subjects: | |
Online Access: | https://risweb.st-andrews.ac.uk/portal/en/researchoutput/learning-deep-models-from-synthetic-data-for-extracting-dolphin-whistle-contours(6a04a536-b73b-44db-8fe2-9886b53aaba3).html https://doi.org/10.1109/IJCNN48605.2020.9206992 http://www.scopus.com/inward/record.url?scp=85093866240&partnerID=8YFLogxK |
id |
ftunstandrewcris:oai:risweb.st-andrews.ac.uk:publications/6a04a536-b73b-44db-8fe2-9886b53aaba3 |
---|---|
record_format |
openpolar |
spelling |
ftunstandrewcris:oai:risweb.st-andrews.ac.uk:publications/6a04a536-b73b-44db-8fe2-9886b53aaba3 2023-05-15T18:33:30+02:00 Learning Deep Models from Synthetic Data for Extracting Dolphin Whistle Contours Li, Pu Liu, Xiaobai Palmer, K. J. Fleishman, Erica Gillespie, Douglas Nosal, Eva Marie Shiu, Yu Klinck, Holger Cholewiak, Danielle Helble, Tyler Roch, Marie A. 2020-07 https://risweb.st-andrews.ac.uk/portal/en/researchoutput/learning-deep-models-from-synthetic-data-for-extracting-dolphin-whistle-contours(6a04a536-b73b-44db-8fe2-9886b53aaba3).html https://doi.org/10.1109/IJCNN48605.2020.9206992 http://www.scopus.com/inward/record.url?scp=85093866240&partnerID=8YFLogxK eng eng Institute of Electrical and Electronics Engineers Inc. info:eu-repo/semantics/restrictedAccess Li , P , Liu , X , Palmer , K J , Fleishman , E , Gillespie , D , Nosal , E M , Shiu , Y , Klinck , H , Cholewiak , D , Helble , T & Roch , M A 2020 , Learning Deep Models from Synthetic Data for Extracting Dolphin Whistle Contours . in 2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings . , 9206992 , Proceedings of the International Joint Conference on Neural Networks , Institute of Electrical and Electronics Engineers Inc. , 2020 International Joint Conference on Neural Networks, IJCNN 2020 , Virtual, Glasgow , United Kingdom , 19/07/20 . https://doi.org/10.1109/IJCNN48605.2020.9206992 acoustic data synthesis deep neural network odontocetes Whistle contour extraction contributionToPeriodical 2020 ftunstandrewcris https://doi.org/10.1109/IJCNN48605.2020.9206992 2022-06-02T07:54:25Z We present a learning-based method for extracting whistles of toothed whales (Odontoceti) in hydrophone recordings. Our method represents audio signals as time-frequency spectrograms and decomposes each spectrogram into a set of time-frequency patches. A deep neural network learns archetypical patterns (e.g., crossings, frequency modulated sweeps) from the spectrogram patches and predicts time-frequency peaks that are associated with whistles. We also developed a comprehensive method to synthesize training samples from background environments and train the network with minimal human annotation effort. We applied the proposed learn-from-synthesis method to a subset of the public Detection, Classification, Localization, and Density Estimation (DCLDE) 2011 workshop data to extract whistle confidence maps, which we then processed with an existing contour extractor to produce whistle annotations. The F1-score of our best synthesis method was 0.158 greater than our baseline whistle extraction algorithm (~25% improvement) when applied to common dolphin (Delphinus spp.) and bottlenose dolphin (Tursiops truncatus) whistles. Other Non-Article Part of Journal/Newspaper toothed whales University of St Andrews: Research Portal 2020 International Joint Conference on Neural Networks (IJCNN) 1 10 |
institution |
Open Polar |
collection |
University of St Andrews: Research Portal |
op_collection_id |
ftunstandrewcris |
language |
English |
topic |
acoustic data synthesis deep neural network odontocetes Whistle contour extraction |
spellingShingle |
acoustic data synthesis deep neural network odontocetes Whistle contour extraction Li, Pu Liu, Xiaobai Palmer, K. J. Fleishman, Erica Gillespie, Douglas Nosal, Eva Marie Shiu, Yu Klinck, Holger Cholewiak, Danielle Helble, Tyler Roch, Marie A. Learning Deep Models from Synthetic Data for Extracting Dolphin Whistle Contours |
topic_facet |
acoustic data synthesis deep neural network odontocetes Whistle contour extraction |
description |
We present a learning-based method for extracting whistles of toothed whales (Odontoceti) in hydrophone recordings. Our method represents audio signals as time-frequency spectrograms and decomposes each spectrogram into a set of time-frequency patches. A deep neural network learns archetypical patterns (e.g., crossings, frequency modulated sweeps) from the spectrogram patches and predicts time-frequency peaks that are associated with whistles. We also developed a comprehensive method to synthesize training samples from background environments and train the network with minimal human annotation effort. We applied the proposed learn-from-synthesis method to a subset of the public Detection, Classification, Localization, and Density Estimation (DCLDE) 2011 workshop data to extract whistle confidence maps, which we then processed with an existing contour extractor to produce whistle annotations. The F1-score of our best synthesis method was 0.158 greater than our baseline whistle extraction algorithm (~25% improvement) when applied to common dolphin (Delphinus spp.) and bottlenose dolphin (Tursiops truncatus) whistles. |
format |
Other Non-Article Part of Journal/Newspaper |
author |
Li, Pu Liu, Xiaobai Palmer, K. J. Fleishman, Erica Gillespie, Douglas Nosal, Eva Marie Shiu, Yu Klinck, Holger Cholewiak, Danielle Helble, Tyler Roch, Marie A. |
author_facet |
Li, Pu Liu, Xiaobai Palmer, K. J. Fleishman, Erica Gillespie, Douglas Nosal, Eva Marie Shiu, Yu Klinck, Holger Cholewiak, Danielle Helble, Tyler Roch, Marie A. |
author_sort |
Li, Pu |
title |
Learning Deep Models from Synthetic Data for Extracting Dolphin Whistle Contours |
title_short |
Learning Deep Models from Synthetic Data for Extracting Dolphin Whistle Contours |
title_full |
Learning Deep Models from Synthetic Data for Extracting Dolphin Whistle Contours |
title_fullStr |
Learning Deep Models from Synthetic Data for Extracting Dolphin Whistle Contours |
title_full_unstemmed |
Learning Deep Models from Synthetic Data for Extracting Dolphin Whistle Contours |
title_sort |
learning deep models from synthetic data for extracting dolphin whistle contours |
publisher |
Institute of Electrical and Electronics Engineers Inc. |
publishDate |
2020 |
url |
https://risweb.st-andrews.ac.uk/portal/en/researchoutput/learning-deep-models-from-synthetic-data-for-extracting-dolphin-whistle-contours(6a04a536-b73b-44db-8fe2-9886b53aaba3).html https://doi.org/10.1109/IJCNN48605.2020.9206992 http://www.scopus.com/inward/record.url?scp=85093866240&partnerID=8YFLogxK |
genre |
toothed whales |
genre_facet |
toothed whales |
op_source |
Li , P , Liu , X , Palmer , K J , Fleishman , E , Gillespie , D , Nosal , E M , Shiu , Y , Klinck , H , Cholewiak , D , Helble , T & Roch , M A 2020 , Learning Deep Models from Synthetic Data for Extracting Dolphin Whistle Contours . in 2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings . , 9206992 , Proceedings of the International Joint Conference on Neural Networks , Institute of Electrical and Electronics Engineers Inc. , 2020 International Joint Conference on Neural Networks, IJCNN 2020 , Virtual, Glasgow , United Kingdom , 19/07/20 . https://doi.org/10.1109/IJCNN48605.2020.9206992 |
op_rights |
info:eu-repo/semantics/restrictedAccess |
op_doi |
https://doi.org/10.1109/IJCNN48605.2020.9206992 |
container_title |
2020 International Joint Conference on Neural Networks (IJCNN) |
container_start_page |
1 |
op_container_end_page |
10 |
_version_ |
1766218120435859456 |