{"id":"https://openalex.org/W4401609070","doi":"https://doi.org/10.1109/icasspw62465.2024.10627576","title":"Self-Supervised Learning for Few-Shot Bird Sound Classification","display_name":"Self-Supervised Learning for Few-Shot Bird Sound Classification","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401609070","doi":"https://doi.org/10.1109/icasspw62465.2024.10627576"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10627576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10627576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://imt-atlantique.hal.science/hal-04925735/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010372672","display_name":"Ilyass Moummad","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I161929037","display_name":"Universit\u00e9 de Bretagne Occidentale","ror":"https://ror.org/01b8h3982","country_code":"FR","type":"education","lineage":["https://openalex.org/I161929037"]},{"id":"https://openalex.org/I4210123702","display_name":"Laboratoire des Sciences et Techniques de l\u2019Information de la Communication et de la Connaissance","ror":"https://ror.org/0266kfd37","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I180375564","https://openalex.org/I201181511","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I4210123702","https://openalex.org/I4210127572","https://openalex.org/I4210145102","https://openalex.org/I4210148559","https://openalex.org/I4210159245","https://openalex.org/I4405260085"]},{"id":"https://openalex.org/I4210127572","display_name":"IMT Atlantique","ror":"https://ror.org/030hj3061","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210127572"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ilyass Moummad","raw_affiliation_strings":["UMR CNRS,IMT Atlantique, Lab-STICC,Brest,France,6285"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMR CNRS,IMT Atlantique, Lab-STICC,Brest,France,6285","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I161929037","https://openalex.org/I4210123702","https://openalex.org/I4210127572"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073128964","display_name":"Nicolas Farrugia","orcid":"https://orcid.org/0000-0002-1159-3513"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I161929037","display_name":"Universit\u00e9 de Bretagne Occidentale","ror":"https://ror.org/01b8h3982","country_code":"FR","type":"education","lineage":["https://openalex.org/I161929037"]},{"id":"https://openalex.org/I4210123702","display_name":"Laboratoire des Sciences et Techniques de l\u2019Information de la Communication et de la Connaissance","ror":"https://ror.org/0266kfd37","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I180375564","https://openalex.org/I201181511","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I4210123702","https://openalex.org/I4210127572","https://openalex.org/I4210145102","https://openalex.org/I4210148559","https://openalex.org/I4210159245","https://openalex.org/I4405260085"]},{"id":"https://openalex.org/I4210127572","display_name":"IMT Atlantique","ror":"https://ror.org/030hj3061","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210127572"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Farrugia","raw_affiliation_strings":["UMR CNRS,IMT Atlantique, Lab-STICC,Brest,France,6285"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMR CNRS,IMT Atlantique, Lab-STICC,Brest,France,6285","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I161929037","https://openalex.org/I4210123702","https://openalex.org/I4210127572"]}]},{"author_position":"last","author":{"id":null,"display_name":"Romain Serizel","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Romain Serizel","raw_affiliation_strings":["University of Lorraine, CNRS,Nancy,France,54000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Lorraine, CNRS,Nancy,France,54000","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I90183372"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"600","last_page":"604"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6109640598297119},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6100238561630249},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.601804256439209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5038661360740662},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.48585888743400574},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36336731910705566},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16105034947395325},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09516748785972595},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05581820011138916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6109640598297119},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6100238561630249},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.601804256439209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5038661360740662},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.48585888743400574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36336731910705566},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16105034947395325},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09516748785972595},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05581820011138916},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10627576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10627576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04925735v1","is_oa":true,"landing_page_url":"https://imt-atlantique.hal.science/hal-04925735","pdf_url":"https://imt-atlantique.hal.science/hal-04925735/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSPW 2024: IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, Apr 2024, Seoul, South Korea. ⟨10.1109/ICASSPW62465.2024.10627576⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04925735v1","is_oa":true,"landing_page_url":"https://imt-atlantique.hal.science/hal-04925735","pdf_url":"https://imt-atlantique.hal.science/hal-04925735/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSPW 2024: IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, Apr 2024, Seoul, South Korea. ⟨10.1109/ICASSPW62465.2024.10627576⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.4399999976158142,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401609070.pdf","grobid_xml":"https://content.openalex.org/works/W4401609070.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2767754137","https://openalex.org/W2982083293","https://openalex.org/W3011702533","https://openalex.org/W3015995734","https://openalex.org/W3094550259","https://openalex.org/W3121931845","https://openalex.org/W3137857706","https://openalex.org/W3202820684","https://openalex.org/W4226051760","https://openalex.org/W4287812705","https://openalex.org/W4294831657","https://openalex.org/W4312891522","https://openalex.org/W4366208220","https://openalex.org/W4385741800","https://openalex.org/W4387390256","https://openalex.org/W4390060493","https://openalex.org/W4392904804","https://openalex.org/W6774314701","https://openalex.org/W6776700526","https://openalex.org/W6784802156","https://openalex.org/W6791742336","https://openalex.org/W6851800889","https://openalex.org/W6857039153"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,82],"(SSL)":[2],"in":[3,12,27,80],"audio":[4,57,101],"holds":[5],"significant":[6],"potential":[7],"across":[8],"various":[9],"domains,":[10],"particularly":[11],"situations":[13],"where":[14,29],"abundant,":[15],"unlabeled":[16],"data":[17],"is":[18,25,47],"readily":[19],"available":[20],"at":[21],"no":[22],"cost.":[23],"This":[24],"pertinent":[26],"bioacoustics,":[28],"biologists":[30],"routinely":[31],"collect":[32],"extensive":[33],"sound":[34],"datasets":[35],"from":[36,56],"the":[37,60,72,106,109],"natural":[38],"environment.":[39],"In":[40],"this":[41],"study,":[42],"we":[43,86],"demonstrate":[44],"that":[45,67,88],"SSL":[46],"capable":[48],"of":[49,53,108],"acquiring":[50],"meaningful":[51],"representations":[52,70],"bird":[54,78,93],"sounds":[55],"recordings":[58],"without":[59],"need":[61],"for":[62,95],"annotations.":[63],"Our":[64],"experiments":[65],"showcase":[66],"these":[68],"learned":[69,110],"exhibit":[71],"capacity":[73],"to":[74,76],"generalize":[75],"new":[77],"species":[79],"few-shot":[81],"(FSL)":[83],"scenarios.":[84],"Additionally,":[85],"show":[87],"selecting":[89],"windows":[90],"with":[91],"high":[92],"activation":[94],"self-supervised":[96],"learning,":[97],"using":[98],"a":[99],"pretrained":[100],"neural":[102],"network,":[103],"significantly":[104],"enhances":[105],"quality":[107],"representations.1":[113]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}