More than a whistle: Automated detection of marine sound sources with a convolutional neural network

Simple item page
dc.contributor.authorWhite, Ellen L.
dc.contributor.authorWhite, Paul R.
dc.contributor.authorBull, Jonathan M.
dc.contributor.authorRisch, Denise
dc.contributor.authorBeck, Suzanne
dc.contributor.authorEdwards, Ewan W.J.
dc.date.accessioned2022-10-21T12:43:56Z
dc.date.available2022-10-21T12:43:56Z
dc.date.issued2022-10-04
dc.descriptionPublication history: Accepted - 14 September 2022; Published online - 04 October 2022en_US
dc.description.abstractThe effective analysis of Passive Acoustic Monitoring (PAM) data has the potential to determine spatial and temporal variations in ecosystem health and species presence if automated detection and classification algorithms are capable of discrimination between marine species and the presence of anthropogenic and environmental noise. Extracting more than a single sound source or call type will enrich our understanding of the interaction between biological, anthropogenic and geophonic soundscape components in the marine environment. Advances in extracting ecologically valuable cues from the marine environment, embedded within the soundscape, are limited by the time required for manual analyses and the accuracy of existing algorithms when applied to large PAM datasets. In this work, a deep learning model is trained for multi-class marine sound source detection using cloud computing to explore its utility for extracting sound sources for use in marine mammal conservation and ecosystem monitoring. A training set is developed comprising existing datasets amalgamated across geographic, temporal and spatial scales, collected across a range of acoustic platforms. Transfer learning is used to fine-tune an open-source state-of-the-art ‘small-scale’ convolutional neural network (CNN) to detect odontocete tonal and broadband call types and vessel noise (from 0 to 48 kHz). The developed CNN architecture uses a custom image input to exploit the differences in temporal and frequency characteristics between each sound source. Each sound source is identified with high accuracy across various test conditions, including variable signal-to-noise-ratio. We evaluate the effect of ambient noise on detector performance, outlining the importance of understanding the variability of the regional soundscape for which it will be deployed. Our work provides a computationally low-cost, efficient framework for mining big marine acoustic data, for information on temporal scales relevant to the management of marine protected areas and the conservation of vulnerable species.en_US
dc.description.sponsorshipThis work was supported by the Natural Environmental Research Council [grant number NE/S007210/1]. The COMPASS project has been supported by the EU’s INTERREG VA Programme, managed by the Special EU Programmes Body. The views and opinions expressed in this document do not necessarily reflect those of the European Commission or the Special EU Programmes Body (SEUPB).en_US
dc.identifierhttp://hdl.handle.net/20.500.12518/491
dc.identifier.citationWhite, E.L., White, P.R., Bull, J.M., Risch, D., Beck, S. and Edwards, E.W.J. (2022) ‘More than a whistle: Automated detection of marine sound sources with a convolutional neural network’, Frontiers in Marine Science. Frontiers Media SA. Available at: https://doi.org/10.3389/fmars.2022.879145.en_US
dc.identifier.issn2296-7745
dc.identifier.urihttps://doi.org/10.3389/fmars.2022.879145
dc.language.isoenen_US
dc.publisherFrontiers Mediaen_US
dc.rights© 2022 White, White, Bull, Risch, Beck and Edwards. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.en_US
dc.subjectmarine soundscapesen_US
dc.subjectCNN - convolutional neural networken_US
dc.subjectpassive acoustic monitoringen_US
dc.subjectefficientNet-B0en_US
dc.subjectsound source detectionen_US
dc.subjectmarine mammal acousticsen_US
dc.subjectDelphinidsen_US
dc.titleMore than a whistle: Automated detection of marine sound sources with a convolutional neural networken_US
dc.typeArticleen_US
dcterms.dateAccepted2022-09-14
dcterms.dateSubmitted2022-02-18

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
More than a whistle. Automated detection of marine sound sources with a convolutional neural network.pdf
Size:
10.45 MB
Format:
Adobe Portable Document Format
Description:
Final published version
Download

Collections

Journal Articles