Show simple item record

dc.contributor.authorLauha, Patrik
dc.contributor.authorSomervuo, Panu
dc.contributor.authorLehikoinen, Petteri
dc.contributor.authorGeres, Lisa
dc.contributor.authorRichter, Tobias
dc.contributor.authorSeibold, Sebastian
dc.contributor.authorOvaskainen, Otso
dc.date.accessioned2022-10-26T09:24:58Z
dc.date.available2022-10-26T09:24:58Z
dc.date.issued2022
dc.identifier.citationLauha, P., Somervuo, P., Lehikoinen, P., Geres, L., Richter, T., Seibold, S., & Ovaskainen, O. (2022). Domain‐specific neural networks improve automated bird sound recognition already with small amount of local data. <i>Methods in Ecology and Evolution</i>, <i>13</i>(12), 2799-2810. <a href="https://doi.org/10.1111/2041-210x.14003" target="_blank">https://doi.org/10.1111/2041-210x.14003</a>
dc.identifier.otherCONVID_159209362
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/83704
dc.description.abstractAn automatic bird sound recognition system is a useful tool for collecting data of different bird species for ecological analysis. Together with autonomous recording units (ARUs), such a system provides a possibility to collect bird observations on a scale that no human observer could ever match. During the last decades, progress has been made in the field of automatic bird sound recognition, but recognizing bird species from untargeted soundscape recordings remains a challenge. In this article, we demonstrate the workflow for building a global identification model and adjusting it to perform well on the data of autonomous recorders from a specific region. We show how data augmentation and a combination of global and local data can be used to train a convolutional neural network to classify vocalizations of 101 bird species. We construct a model and train it with a global data set to obtain a base model. The base model is then fine-tuned with local data from Southern Finland in order to adapt it to the sound environment of a specific location and tested with two data sets: one originating from the same Southern Finnish region and another originating from a different region in German Alps. Our results suggest that fine-tuning with local data significantly improves the network performance. Classification accuracy was improved for test recordings from the same area as the local training data (Southern Finland) but not for recordings from a different region (German Alps). Data augmentation enables training with a limited number of training data and even with few local data samples significant improvement over the base model can be achieved. Our model outperforms the current state-of-the-art tool for automatic bird sound classification. Using local data to adjust the recognition model for the target domain leads to improvement over general non-tailored solutions. The process introduced in this article can be applied to build a fine-tuned bird sound classification model for a specific environment.en
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.publisherWiley-Blackwell
dc.relation.ispartofseriesMethods in Ecology and Evolution
dc.rightsCC BY-NC 4.0
dc.subject.otherautonomous recording units
dc.subject.otherbioacoustics
dc.subject.otherbio-monitoring
dc.subject.otherbird sound recognition
dc.subject.otherconvolutional neural networks
dc.subject.otherdeep learning
dc.subject.othermodel fine-tuning
dc.titleDomain‐specific neural networks improve automated bird sound recognition already with small amount of local data
dc.typearticle
dc.identifier.urnURN:NBN:fi:jyu-202210265013
dc.contributor.laitosBio- ja ympäristötieteiden laitosfi
dc.contributor.laitosDepartment of Biological and Environmental Scienceen
dc.type.urihttp://purl.org/eprint/type/JournalArticle
dc.type.coarhttp://purl.org/coar/resource_type/c_2df8fbb1
dc.description.reviewstatuspeerReviewed
dc.format.pagerange2799-2810
dc.relation.issn2041-210X
dc.relation.numberinseries12
dc.relation.volume13
dc.type.versionpublishedVersion
dc.rights.copyright© 2022 The Authors. Methods in Ecology and Evolution published by John Wiley & Sons Ltd on behalf of British Ecological Society.
dc.rights.accesslevelopenAccessfi
dc.relation.grantnumber856506
dc.relation.grantnumber856506
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/H2020/856506/EU//LIFEPLAN
dc.subject.ysohavainnot
dc.subject.ysosyväoppiminen
dc.subject.ysolinnut
dc.subject.ysotunnistaminen
dc.subject.ysoneuroverkot
dc.subject.ysoeläinten äänet
dc.subject.ysokoneoppiminen
dc.format.contentfulltext
jyx.subject.urihttp://www.yso.fi/onto/yso/p5284
jyx.subject.urihttp://www.yso.fi/onto/yso/p39324
jyx.subject.urihttp://www.yso.fi/onto/yso/p3363
jyx.subject.urihttp://www.yso.fi/onto/yso/p8265
jyx.subject.urihttp://www.yso.fi/onto/yso/p7292
jyx.subject.urihttp://www.yso.fi/onto/yso/p14137
jyx.subject.urihttp://www.yso.fi/onto/yso/p21846
dc.rights.urlhttps://creativecommons.org/licenses/by-nc/4.0/
dc.relation.doi10.1111/2041-210x.14003
dc.relation.funderEuropean Commissionen
dc.relation.funderEuroopan komissiofi
jyx.fundingprogramERC European Research Council, H2020en
jyx.fundingprogramERC European Research Council, H2020fi
jyx.fundinginformationOtso Ovaskainen was funded by the Academy of Finland (grant no. 309581), Jane and Aatos Erkko Foundation, Research Council of Norway through its Centres of Excellence Funding Scheme (223257), and the European Research Council (ERC) under the European Union's Horizon 2020 research and in-novation programme (grant agreement No 856506; ERC-synergy project LIFEPLAN).
dc.type.okmA1


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

CC BY-NC 4.0
Except where otherwise noted, this item's license is described as CC BY-NC 4.0