{"id":"https://openalex.org/W3104805957","doi":"https://doi.org/10.1109/icassp39728.2021.9415009","title":"Unsupervised Contrastive Learning of Sound Event Representations","display_name":"Unsupervised Contrastive Learning of Sound Event Representations","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3104805957","doi":"https://doi.org/10.1109/icassp39728.2021.9415009","mag":"3104805957"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9415009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.07616","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025025113","display_name":"Eduardo Fonseca","orcid":"https://orcid.org/0000-0001-9872-3917"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Eduardo Fonseca","raw_affiliation_strings":["Universitat Pompeu Fabra,Music Technology Group,Barcelona"],"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group,Barcelona","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028186506","display_name":"Diego Ortego","orcid":"https://orcid.org/0000-0002-1011-3610"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Diego Ortego","raw_affiliation_strings":["Dublin City University (DCU),Insight Centre for Data Analytics"],"affiliations":[{"raw_affiliation_string":"Dublin City University (DCU),Insight Centre for Data Analytics","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073924795","display_name":"Kevin McGuinness","orcid":"https://orcid.org/0000-0003-1336-6477"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Kevin McGuinness","raw_affiliation_strings":["Dublin City University (DCU),Insight Centre for Data Analytics"],"affiliations":[{"raw_affiliation_string":"Dublin City University (DCU),Insight Centre for Data Analytics","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106498523","display_name":"Noel E. O\u2019Connor","orcid":"https://orcid.org/0000-0002-4033-9135"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Noel E. O'Connor","raw_affiliation_strings":["Dublin City University (DCU),Insight Centre for Data Analytics"],"affiliations":[{"raw_affiliation_string":"Dublin City University (DCU),Insight Centre for Data Analytics","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":["Universitat Pompeu Fabra,Music Technology Group,Barcelona"],"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group,Barcelona","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025025113"],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":1.3885,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.80450776,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"371","last_page":"375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9944999814033508,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7284231781959534},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5686244964599609},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5535396933555603},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5530480146408081},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5173860788345337},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5068715214729309},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.45609816908836365},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44468629360198975},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4386499226093292},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41059356927871704},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3537396788597107}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7284231781959534},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5686244964599609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5535396933555603},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5530480146408081},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5173860788345337},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5068715214729309},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.45609816908836365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44468629360198975},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4386499226093292},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41059356927871704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3537396788597107},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1109/icassp39728.2021.9415009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:doras.dcu.ie:25575","is_oa":false,"landing_page_url":"http://doras.dcu.ie/25575/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401511","display_name":"Dublin City University Open Access Institutional Repository (Dublin City University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I42934936","host_organization_name":"Dublin City University","host_organization_lineage":["https://openalex.org/I42934936"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"  Fonseca, Eduardo ORCID: 0000-0001-9872-3917 <https://orcid.org/0000-0001-9872-3917>, Ortego, Diego ORCID: 0000-0002-1011-3610 <https://orcid.org/0000-0002-1011-3610>, McGuinness, Kevin ORCID: 0000-0003-1336-6477 <https://orcid.org/0000-0003-1336-6477>, O'Connor, Noel E. ORCID: 0000-0002-4033-9135 <https://orcid.org/0000-0002-4033-9135> and Serra, Xavier ORCID: 0000-0003-1395-2345 <https://orcid.org/0000-0003-1395-2345>  (2021) Unsupervised contrastive learning of sound event representations.  In: IEEE International Conference on Acoustics, Speech and Signal Processing, 6-11 June 2021, Toronto, Canada (Online).      ","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:repositori-api.upf.edu:10230/56076","is_oa":false,"landing_page_url":"http://hdl.handle.net/10230/56076","pdf_url":null,"source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/acceptedVersion"},{"id":"pmh:oai:arXiv.org:2011.07616","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.07616","pdf_url":"https://arxiv.org/pdf/2011.07616","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3104805957","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.07616","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:repositori.upf.edu:10230/56076","is_oa":false,"landing_page_url":"https://repositori.upf.edu/bitstreams/107651d4-cc3c-4a6a-beb6-94c4325731a2/download","pdf_url":null,"source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2011.07616","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.07616","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/j4wt-cw78","is_oa":true,"landing_page_url":"https://doi.org/10.17023/j4wt-cw78","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.07616","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.07616","pdf_url":"https://arxiv.org/pdf/2011.07616","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2194775991","https://openalex.org/W2593116425","https://openalex.org/W2767754137","https://openalex.org/W2770119437","https://openalex.org/W2798991696","https://openalex.org/W2842511635","https://openalex.org/W2912237282","https://openalex.org/W2936774411","https://openalex.org/W2941964676","https://openalex.org/W2963560275","https://openalex.org/W2963859210","https://openalex.org/W2963906190","https://openalex.org/W2982343573","https://openalex.org/W2982449249","https://openalex.org/W2986739609","https://openalex.org/W2997570773","https://openalex.org/W2998559948","https://openalex.org/W3007373432","https://openalex.org/W3009561768","https://openalex.org/W3015622757","https://openalex.org/W3015949486","https://openalex.org/W3021910945","https://openalex.org/W3034978746","https://openalex.org/W3039910566","https://openalex.org/W3090388844","https://openalex.org/W3101133634","https://openalex.org/W3106428938","https://openalex.org/W3116298410","https://openalex.org/W4256604311","https://openalex.org/W6746278845","https://openalex.org/W6753583920","https://openalex.org/W6758930985","https://openalex.org/W6761903662","https://openalex.org/W6769522157","https://openalex.org/W6774314701","https://openalex.org/W6774670964","https://openalex.org/W6774730124","https://openalex.org/W6777179611","https://openalex.org/W6780483730","https://openalex.org/W6782004394","https://openalex.org/W6783462664","https://openalex.org/W6785591002"],"related_works":["https://openalex.org/W2593116425","https://openalex.org/W3093563057","https://openalex.org/W3035524453","https://openalex.org/W2842511635","https://openalex.org/W3035955399","https://openalex.org/W3130223764","https://openalex.org/W2895106137","https://openalex.org/W3165998135","https://openalex.org/W3166784900","https://openalex.org/W3166081780","https://openalex.org/W3177393777","https://openalex.org/W2887108625","https://openalex.org/W3096655658","https://openalex.org/W3005680577","https://openalex.org/W3206818284","https://openalex.org/W3184031704","https://openalex.org/W3128140268","https://openalex.org/W1494485407","https://openalex.org/W3158388938","https://openalex.org/W3015817524"],"abstract_inverted_index":{"Self-supervised":[0],"representation":[1],"learning":[2,32],"can":[3,123],"mitigate":[4,124],"the":[5,48,79,90,125],"limitations":[6],"in":[7,21,97],"recognition":[8],"tasks":[9],"with":[10,69],"few":[11],"manually":[12,108],"labeled":[13,109,114],"data":[14,75,128],"but":[15],"abundant":[16],"unlabeled":[17],"data\u2014a":[18],"common":[19],"scenario":[20],"sound":[22,38,57,101],"event":[23,39,102],"research.":[24],"In":[25],"this":[26,42],"work,":[27],"we":[28,44],"explore":[29],"unsupervised":[30,120],"contrastive":[31,121],"as":[33],"a":[34],"way":[35],"to":[36,46],"learn":[37],"representations.":[40],"To":[41],"end,":[43],"propose":[45],"use":[47],"pretext":[49],"task":[50],"of":[51,56,66,82,127],"contrasting":[52],"differently":[53],"augmented":[54],"views":[55,60],"events.":[58],"The":[59],"are":[61],"computed":[62],"primarily":[63],"via":[64,85],"mixing":[65],"training":[67],"examples":[68],"unrelated":[70],"backgrounds,":[71],"followed":[72],"by":[73],"other":[74],"augmentations.":[76],"We":[77,88],"analyze":[78],"main":[80],"components":[81],"our":[83],"method":[84],"ablation":[86],"experiments.":[87],"evaluate":[89],"learned":[91],"representations":[92],"using":[93,106,112],"linear":[94],"evaluation,":[95],"and":[96,111,130],"two":[98],"in-domain":[99],"downstream":[100],"classification":[103],"tasks,":[104],"namely,":[105],"limited":[107],"data,":[110],"noisy":[113,134],"data.":[115],"Our":[116],"results":[117],"suggest":[118],"that":[119],"pre-training":[122],"impact":[126],"scarcity":[129],"increase":[131],"robustness":[132],"against":[133],"labels.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":8}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}