{"datasetrec":{"DasID":8543,"Acronym":null,"StandardTitle":"Acoustic salient event annotations","OrigTitle":null,"OrigTitleLangID":null,"OrigTitleLangCode":null,"OrigTitleLang":null,"OrigTitleLangNL":null,"VersionName":null,"ContactEmail":null,"VersionDate":null,"VersionDay":null,"VersionMonth":null,"VersionYear":null,"SizeReference":null,"EngAbstract":"This repository contains all the data used to produce the results of the publication Parcerisas, C.; Schall, E.; Te Velde, K.; Botteldooren, D.; Devos, P.; Debusschere, E. Machine learning for efficient segregation and labeling of potential biological sounds in long-term underwater recordings (2024). Frontiers in Remote Sensing. doi: 10.3389/frsen.2024.1390687 All the necessary scripts to reproduce the publication results can be found on through github: <a href=\"https://github.com/lifewatch/sound-segregation-and-categorization\"> https://github.com/lifewatch/sound-segregation-and-categorization</a>.","EngDescr":"Studying marine soundscapes by detecting known sound events and quantifying their spatio-temporal patterns can provide ecologically relevant information. However, the exploration of underwater sound data to find and identify possible sound events of interest can be highly time-intensive for human analysts. To speed up this process, we propose a novel methodology that first detects all the potentially relevant acoustic events and then clusters them in an unsupervised way prior to manual revision. We demonstrate its applicability on a short deployment. To detect acoustic events, a deep learning object detection algorithm from computer vision (YOLOv8) is re-trained to detect any (short) acoustic event. This is done by converting the audio to spectrograms using sliding windows longer than the expected sound events of interest. The model detects any event present on that window and provides their time and frequency limits. With this approach, multiple events happening simultaneously can be detected. To further explore the possibilities to limit the human input needed to create the annotations to train the model, we propose an active learning approach to select the most informative audio files in an iterative manner for subsequent manual annotation. The obtained detection models are trained and tested on a dataset from the Belgian Part of the North Sea, and then further evaluated for robustness on a freshwater dataset from major European rivers. The proposed active learning approach outperforms the random selection of files, both in the marine and the freshwater datasets. Once the events are detected, they are converted to an embedded feature space using the BioLingual model, which is trained to classify different (biological) sounds. The obtained representations are then clustered in an unsupervised way, obtaining different sound classes. These classes are then manually revised. This method can be applied to unseen data as a tool to help bioacousticians identify recurrent sounds and save time when studying their spatio-temporal patterns. This reduces the time researchers need to go through long acoustic recordings and allows to conduct a more targeted analysis. It also provides a framework to monitor soundscapes regardless of whether the sound sources are known or not.","OrigAbstract":null,"OrigDescr":null,"Comments":null,"ReleaseDate":null,"ReleaseDate0":null,"OrigDescrLang":null,"EmbargoDate":null,"OrigDescrLangNL":null,"OrigLangCode":null,"OrigLangCodeExtended":null,"OrigLangID":null,"DescrCompFlag":0,"DescrTransFlag":0,"Citation":"Parcerisas, C.; Schall, E.; Aubach, J.; Te Velde, K.; Slabbekoorn, H.; Debusschere, E.; Flanders Marine Institute (VLIZ); Alfred Wegener Institute; Leiden University; (2024): Acoustic salient event annotations. Marine Data Archive.","AccessConstraints":null,"UDate":"2024-06-11","CDate":"2024-04-08","CurrencyDate":null,"RevisionDate":null,"DateLastModified":{"date":"2026-04-03 01:47:42.174469","timezone_type":1,"timezone":"+02:00"},"CheckedFlag":0,"PublicFlag":1,"VlizCoreFlag":1,"MarineFlag":1,"FreshFlag":1,"BrackishFlag":0,"TerrestrialFlag":0,"StatusID":1,"DasType":"Data","DasTypeID":1,"DasOrigin":"Monitoring: field survey","Progress":"Completed","AccessConstraint":"Attribution (CC BY)","AccConstrEN":"Attribution (CC BY)","AccConstrDisplay":"<a rel=\"license\" href=\"https://creativecommons.org/licenses/by/4.0/\" target=\"_blank\"><img alt=\"Creative Commons License\" style=\"border:0px;height:15px;width:80px;vertical-align:middle;\" src=\"https://www.marinespecies.org/aphia/images/cc/by.png\" /></a> This dataset is licensed under a <a rel=\"license\" href=\"https://creativecommons.org/licenses/by/4.0/\" target=\"_blank\">Creative Commons Attribution 4.0 International License</a>.","License":"https://creativecommons.org/licenses/by/4.0/","AccConstrDescription":"This license lets others distribute, remix, tweak, and build upon your work, even commercially, as long as they credit you for the original creation. This is the most accommodating of licenses offered. Recommended for maximum dissemination and use of licensed materials.","Lineage":null,"AccConID":21},"dois":[{"DOIID":988,"PublicationYear":2024,"DOI":"10.14284/667","Citation":"Parcerisas, C.; Schall, E.; Aubach, J.; Te Velde, K.; Slabbekoorn, H.; Debusschere, E.; Flanders Marine Institute (VLIZ); Alfred Wegener Institute; Leiden University; (2024): Acoustic salient event annotations. Marine Data Archive.","MDAID":"VLIZ_00000776_6612aa49a2128862248933","Moratorium":0,"MDAURL":"https://mda.vliz.be/directlink.php?fid=VLIZ_00000776_6612aa49a2128862248933","CurrentDOI":1,"Active":1,"URL":null,"downloadURL":"https://mda.vliz.be/download.php?file=VLIZ_00000776_6612aa49a2128862248933"}],"spcols":null,"keywords":[{"ThesaurusTerm":"Acoustic data","ThesTypID":1,"ThesType":"ASFA Thesaurus List","Code":"c_54b338c3","Description":null,"OrigThesTerm":"Acoustic data","DutchTerm":null,"URI":"http://aims.fao.org/aos/agrovoc/c_54b338c3","DasKeywordDescr":null},{"ThesaurusTerm":"Annotations","ThesTypID":2,"ThesType":"CSA Technology Research Database Master Thesaurus","Code":null,"Description":null,"OrigThesTerm":"Annotations","DutchTerm":null,"URI":null,"DasKeywordDescr":null},{"ThesaurusTerm":"Europe","ThesTypID":34,"ThesType":"ASFA Geoterms","Code":null,"Description":null,"OrigThesTerm":"Europe","DutchTerm":null,"URI":null,"DasKeywordDescr":null},{"ThesaurusTerm":"Event detection","ThesTypID":0,"ThesType":null,"Code":null,"Description":null,"OrigThesTerm":"Event detection","DutchTerm":null,"URI":null,"DasKeywordDescr":null},{"ThesaurusTerm":"Underwater raw acoustic files","ThesTypID":0,"ThesType":null,"Code":null,"Description":null,"OrigThesTerm":"Underwater raw acoustic files","DutchTerm":null,"URI":null,"DasKeywordDescr":null},{"ThesaurusTerm":"Unknown underwater sounds","ThesTypID":0,"ThesType":null,"Code":null,"Description":null,"OrigThesTerm":"Unknown underwater sounds","DutchTerm":null,"URI":null,"DasKeywordDescr":null}],"parents":[{"DasID":7879,"Acronym":"PhD_Parcerisas","EngAbstract":"<p>Underwater Acoustic Network recording continuously from 10 Hz to 50 kHz, covering most of geophonic sounds, anthropogenic noise and biophonic events in the Belgian Part of the North Sea.</p>","License":"https://creativecommons.org/licenses/by/4.0/","StandardTitle":"Broadband Acoustic Network dataset","doi":null,"vlizDoi":null},{"DasID":7897,"Acronym":null,"EngAbstract":"Underwater Acoustic Sensor Network recording continuously from 10 Hz to >24 kHz, covering most of geophonic sounds, anthropogenic noise and biophonic events in the Belgian Part of the North Sea.","License":null,"StandardTitle":"Lifewatch observatory data: Broadband acoustic sensor network in the Belgian Part of the North Sea","doi":null,"vlizDoi":null}],"children":null,"othrel":null,"othrelrev":null,"ownerships":[{"OrderNr":null,"Surname":"Parcerisas","Firstname":"Clea","Initials":"C.","PerPublicFlag":1,"AdrID":162692,"Email":"clea.parcerisas@vliz.be","InsPublicFlag":1,"Acronym":"VLIZ","OrigNameLangCode":"en","OrigNameLangID":15,"FullOrigName":"Flanders Marine Institute","InsOwnerCNT":4,"PersID":38082,"InsID":36,"FullInstitute":"Vlaams Instituut voor de Zee","RoleID":61,"Role":"Data creator","OrigName":"Flanders Marine Institute","StandardName":"Vlaams Instituut voor de Zee","FullAcronym":"VLIZ","ORC":"https://orcid.org/0000-0001-7466-0288","ROR":"https://ror.org/0496vr396"},{"OrderNr":null,"Surname":"Parcerisas","Firstname":"Clea","Initials":"C.","PerPublicFlag":1,"AdrID":null,"Email":null,"InsPublicFlag":null,"Acronym":null,"OrigNameLangCode":null,"OrigNameLangID":null,"FullOrigName":null,"InsOwnerCNT":0,"PersID":38082,"InsID":null,"FullInstitute":null,"RoleID":24,"Role":"Contact","OrigName":null,"StandardName":null,"FullAcronym":null,"ORC":"https://orcid.org/0000-0001-7466-0288","ROR":null},{"OrderNr":null,"Surname":"Schall","Firstname":"Elena","Initials":"E.","PerPublicFlag":1,"AdrID":168067,"Email":"elena.schall@awi.de","InsPublicFlag":1,"Acronym":"OZA","OrigNameLangCode":null,"OrigNameLangID":null,"FullOrigName":null,"InsOwnerCNT":2,"PersID":44921,"InsID":15338,"FullInstitute":"Alfred Wegener Institute for Polar- and Marine Research; Ocean Acoustics Group","RoleID":61,"Role":"Data creator","OrigName":null,"StandardName":"Ocean Acoustics Group","FullAcronym":"AWI-OZA","ORC":"https://orcid.org/0000-0002-7740-5466","ROR":null},{"OrderNr":null,"Surname":"Aubach","Firstname":"Julia","Initials":"J.","PerPublicFlag":1,"AdrID":171082,"Email":"julia.aubach@vliz.be","InsPublicFlag":1,"Acronym":"VLIZ","OrigNameLangCode":"en","OrigNameLangID":15,"FullOrigName":"Flanders Marine Institute","InsOwnerCNT":4,"PersID":45098,"InsID":36,"FullInstitute":"Vlaams Instituut voor de Zee","RoleID":61,"Role":"Data creator","OrigName":"Flanders Marine Institute","StandardName":"Vlaams Instituut voor de Zee","FullAcronym":"VLIZ","ORC":"https://orcid.org/0009-0001-4724-3558","ROR":"https://ror.org/0496vr396"},{"OrderNr":null,"Surname":"te Velde","Firstname":"Kees","Initials":"K.","PerPublicFlag":1,"AdrID":168064,"Email":"k.te.velde@biology.leidenuniv.nl","InsPublicFlag":1,"Acronym":null,"OrigNameLangCode":null,"OrigNameLangID":null,"FullOrigName":null,"InsOwnerCNT":3,"PersID":45269,"InsID":9708,"FullInstitute":"Universiteit Leiden; Faculteit Wetenschappen; Institute of Biology","RoleID":61,"Role":"Data creator","OrigName":null,"StandardName":"Institute of Biology","FullAcronym":null,"ORC":"https://orcid.org/0009-0005-5479-6424","ROR":null},{"OrderNr":null,"Surname":"Slabbekoorn","Firstname":"Hans","Initials":"H.","PerPublicFlag":1,"AdrID":160678,"Email":"h.w.slabbekoorn@biology.leidenuniv.nl","InsPublicFlag":1,"Acronym":null,"OrigNameLangCode":null,"OrigNameLangID":null,"FullOrigName":null,"InsOwnerCNT":3,"PersID":35322,"InsID":9708,"FullInstitute":"Universiteit Leiden; Faculteit Wetenschappen; Institute of Biology","RoleID":61,"Role":"Data creator","OrigName":null,"StandardName":"Institute of Biology","FullAcronym":null,"ORC":"https://orcid.org/0000-0003-2309-0048","ROR":null},{"OrderNr":null,"Surname":"Debusschere","Firstname":"Elisabeth","Initials":"E.","PerPublicFlag":1,"AdrID":167751,"Email":"elisabeth.debusschere@vliz.be","InsPublicFlag":1,"Acronym":"VLIZ","OrigNameLangCode":"en","OrigNameLangID":15,"FullOrigName":"Flanders Marine Institute","InsOwnerCNT":4,"PersID":25977,"InsID":36,"FullInstitute":"Vlaams Instituut voor de Zee","RoleID":61,"Role":"Data creator","OrigName":"Flanders Marine Institute","StandardName":"Vlaams Instituut voor de Zee","FullAcronym":"VLIZ","ORC":"https://orcid.org/0000-0002-5595-0295","ROR":"https://ror.org/0496vr396"},{"OrderNr":null,"Surname":null,"Firstname":null,"Initials":null,"PerPublicFlag":null,"AdrID":null,"Email":null,"InsPublicFlag":1,"Acronym":"VLIZ","OrigNameLangCode":"en","OrigNameLangID":15,"FullOrigName":"Flanders Marine Institute","InsOwnerCNT":4,"PersID":null,"InsID":36,"FullInstitute":"Vlaams Instituut voor de Zee","RoleID":61,"Role":"Data creator","OrigName":"Flanders Marine Institute","StandardName":"Vlaams Instituut voor de Zee","FullAcronym":"VLIZ","ORC":null,"ROR":"https://ror.org/0496vr396"},{"OrderNr":null,"Surname":null,"Firstname":null,"Initials":null,"PerPublicFlag":null,"AdrID":null,"Email":null,"InsPublicFlag":1,"Acronym":"OZA","OrigNameLangCode":null,"OrigNameLangID":null,"FullOrigName":null,"InsOwnerCNT":2,"PersID":null,"InsID":15338,"FullInstitute":"Alfred Wegener Institute for Polar- and Marine Research; Ocean Acoustics Group","RoleID":61,"Role":"Data creator","OrigName":null,"StandardName":"Ocean Acoustics Group","FullAcronym":"AWI-OZA","ORC":null,"ROR":null},{"OrderNr":null,"Surname":null,"Firstname":null,"Initials":null,"PerPublicFlag":null,"AdrID":null,"Email":null,"InsPublicFlag":1,"Acronym":null,"OrigNameLangCode":null,"OrigNameLangID":null,"FullOrigName":null,"InsOwnerCNT":3,"PersID":null,"InsID":9708,"FullInstitute":"Universiteit Leiden; Faculteit Wetenschappen; Institute of Biology","RoleID":61,"Role":"Data creator","OrigName":null,"StandardName":"Institute of Biology","FullAcronym":null,"ORC":null,"ROR":null}],"taxterms":null,"frameworks":null,"otherterms":[{"OtherTerm":"Event detection"},{"OtherTerm":"Underwater raw acoustic files"},{"OtherTerm":"Unknown underwater sounds"}],"temporal":null,"geographical":[{"GeoTerm":"Belgian part of the North Sea","DasGeoID":14263,"DasGeoTerm":null,"DasID":8543,"GeotID":9478,"X":null,"Y":null,"MaxX":null,"MaxY":null,"StationName":null,"Precision":null,"CoordSystID":null,"GeoDatumID":null,"OrigCoordMinX":null,"OrigCoordMinY":null,"OrigCoordMaxX":null,"OrigCoordMaxY":null,"OrderNr":null,"Projection":null,"GeoDatum":null,"GeoObjectID":26567,"OrigGeoTerm":"Belgian part of the North Sea","DutchTerm":null},{"GeoTerm":"Europe","DasGeoID":14262,"DasGeoTerm":null,"DasID":8543,"GeotID":2005,"X":null,"Y":null,"MaxX":null,"MaxY":null,"StationName":null,"Precision":null,"CoordSystID":null,"GeoDatumID":null,"OrigCoordMinX":null,"OrigCoordMinY":null,"OrigCoordMaxX":null,"OrigCoordMaxY":null,"OrderNr":null,"Projection":null,"GeoDatum":null,"GeoObjectID":1920,"OrigGeoTerm":"Europe","DutchTerm":"Europa"}],"meastypes":[{"MethID":680,"DasMeasTypID":19141,"DasMeasType":"","Matrix":null,"MatrixNL":null,"Parameter":"Acoustic detections","ParameterNL":null,"Description":null,"Unit":null,"Methodology":"Underwater recording","Protocol":null,"QualityControl":null,"Precision":null,"Detectionlimit":null,"Instrument":null,"InstrumentUrl":null,"MethFull":"","ParaCategoryTitle":null,"ParaCatCode":null},{"MethID":679,"DasMeasTypID":19138,"DasMeasType":"","Matrix":null,"MatrixNL":null,"Parameter":"Human annotations","ParameterNL":null,"Description":null,"Unit":null,"Methodology":"Raven Pro","Protocol":null,"QualityControl":null,"Precision":null,"Detectionlimit":null,"Instrument":null,"InstrumentUrl":null,"MethFull":"","ParaCategoryTitle":null,"ParaCatCode":null}],"dasthemes":[{"DasThemeID":101,"DasTheme":"Biology > Acoustics","DasTheme0":"Acoustics","DutchTerm":"Geluid"}],"projects":[{"ProID":5104,"Acronym":null,"Progress":"Completed","StandardTitle":"Marine Soundscapes in Shallow Water: Automated Tools for Characterization and Analysis","FP7Code":null,"GrantDOI":null,"FunderID":null,"FunderIDType":null,"FunderCodes":["Own budget, for example: patrimony, inscription fees, gifts"]}],"refs":[{"0":392078,"BRefID":392078,"1":"Based on this dataset","Relation":"Based on this dataset","2":2,"RelationID":2,"3":"<b>Parcerisas, C. <i>et al.</i></b> (2024). Machine learning for efficient segregation and labeling of potential biological sounds in long-term underwater recordings. <i>Front. Remote Sens. 5</i>: 1390687. <a href=\"https://dx.doi.org/10.3389/frsen.2024.1390687\" target=\"_blank\">https://dx.doi.org/10.3389/frsen.2024.1390687</a>","RR":"<b>Parcerisas, C. <i>et al.</i></b> (2024). Machine learning for efficient segregation and labeling of potential biological sounds in long-term underwater recordings. <i>Front. Remote Sens. 5</i>: 1390687. <a href=\"https://dx.doi.org/10.3389/frsen.2024.1390687\" target=\"_blank\">https://dx.doi.org/10.3389/frsen.2024.1390687</a>","4":"Machine learning for efficient segregation and labeling of potential biological sounds in long-term underwater recordings","StT":"Machine learning for efficient segregation and labeling of potential biological sounds in long-term underwater recordings","5":"Parcerisas, C.; Schall, E.; te Velde, K.; Botteldooren, D.; Devos, P.; Debusschere, E.","RSA":"Parcerisas, C.; Schall, E.; te Velde, K.; Botteldooren, D.; Devos, P.; Debusschere, E.","6":"Gebaseerd op deze dataset","DutchTerm":"Gebaseerd op deze dataset","7":2024,"AnaDate":2024,"8":null,"MonDate":null,"9":". <i>Front. Remote Sens. 5</i>: 1390687. <a href=\"https://dx.doi.org/10.3389/frsen.2024.1390687\" target=\"_blank\">https://dx.doi.org/10.3389/frsen.2024.1390687</a>","":". <i>Front. Remote Sens. 5</i>: 1390687. <a href=\"https://dx.doi.org/10.3389/frsen.2024.1390687\" target=\"_blank\">https://dx.doi.org/10.3389/frsen.2024.1390687</a>","10":"https://dx.doi.org/10.3389/frsen.2024.1390687","doi":"https://dx.doi.org/10.3389/frsen.2024.1390687"},{"0":392485,"BRefID":392485,"1":"Describing this dataset","Relation":"Describing this dataset","2":3,"RelationID":3,"3":"<b>Calonge, A. <i>et al.</i></b> (2026). Scalable low-cost seabed landers: The missing link for sustained, integrated, long-term observations in dynamic shallow seas. <i>Remote Sensing in Ecology and Conservation Online first</i>: 1-9. <a href=\"https://dx.doi.org/10.1002/rse2.70072\" target=\"_blank\">https://dx.doi.org/10.1002/rse2.70072</a>","RR":"<b>Calonge, A. <i>et al.</i></b> (2026). Scalable low-cost seabed landers: The missing link for sustained, integrated, long-term observations in dynamic shallow seas. <i>Remote Sensing in Ecology and Conservation Online first</i>: 1-9. <a href=\"https://dx.doi.org/10.1002/rse2.70072\" target=\"_blank\">https://dx.doi.org/10.1002/rse2.70072</a>","4":"Scalable low-cost seabed landers: The missing link for sustained, integrated, long-term observations in dynamic shallow seas","StT":"Scalable low-cost seabed landers: The missing link for sustained, integrated, long-term observations in dynamic shallow seas","5":"Calonge, A.; Develter, R.; Muñiz, C.; Parcerisas, C.; Reubens, J.; Boone, W.; Deneudt, K.; Debusschere, E.","RSA":"Calonge, A.; Develter, R.; Muñiz, C.; Parcerisas, C.; Reubens, J.; Boone, W.; Deneudt, K.; Debusschere, E.","6":"Beschrijft deze dataset","DutchTerm":"Beschrijft deze dataset","7":2026,"AnaDate":2026,"8":null,"MonDate":null,"9":". <i>Remote Sensing in Ecology and Conservation Online first</i>: 1-9. <a href=\"https://dx.doi.org/10.1002/rse2.70072\" target=\"_blank\">https://dx.doi.org/10.1002/rse2.70072</a>","":". <i>Remote Sensing in Ecology and Conservation Online first</i>: 1-9. <a href=\"https://dx.doi.org/10.1002/rse2.70072\" target=\"_blank\">https://dx.doi.org/10.1002/rse2.70072</a>","10":"https://dx.doi.org/10.1002/rse2.70072","doi":"https://dx.doi.org/10.1002/rse2.70072"}],"urls":null,"pictures":null,"urlmaps":null,"spatreps":null,"fileformats":null,"resmessage":"","complete":1}