{"id":"https://openalex.org/W3093563057","doi":"https://doi.org/10.1109/icassp39728.2021.9413528","title":"Contrastive Learning of General-Purpose Audio Representations","display_name":"Contrastive Learning of General-Purpose Audio Representations","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3093563057","doi":"https://doi.org/10.1109/icassp39728.2021.9413528","mag":"3093563057"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413528","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.10915","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011960578","display_name":"Aaqib Saeed","orcid":"https://orcid.org/0000-0003-1473-0322"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Aaqib Saeed","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065912572","display_name":"David Grangier","orcid":"https://orcid.org/0000-0002-8847-9532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Grangier","raw_affiliation_strings":["Google Research, Paris, France","Google Research,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Paris, France","institution_ids":[]},{"raw_affiliation_string":"Google Research,Paris,France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047639590","display_name":"Neil Zeghidour","orcid":"https://orcid.org/0000-0001-6896-3987"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Neil Zeghidour","raw_affiliation_strings":["Google Research, Paris, France","Google Research,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Paris, France","institution_ids":[]},{"raw_affiliation_string":"Google Research,Paris,France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.1582,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.98729983,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3875","last_page":"3879"},"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":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8190972805023193},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6272820830345154},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5885723233222961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5664846301078796},{"id":"https://openalex.org/keywords/cola","display_name":"Cola (plant)","score":0.5524317026138306},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4832204580307007},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4781702160835266},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4781292974948883},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43398967385292053},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.43330201506614685},{"id":"https://openalex.org/keywords/simplicity","display_name":"Simplicity","score":0.4238075613975525},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36687391996383667},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12484806776046753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8190972805023193},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6272820830345154},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5885723233222961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5664846301078796},{"id":"https://openalex.org/C2781138811","wikidata":"https://www.wikidata.org/wiki/Q114264","display_name":"Cola (plant)","level":2,"score":0.5524317026138306},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4832204580307007},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4781702160835266},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4781292974948883},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43398967385292053},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.43330201506614685},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.4238075613975525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36687391996383667},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12484806776046753},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413528","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:arXiv.org:2010.10915","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.10915","pdf_url":"https://arxiv.org/pdf/2010.10915","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/13c01281-c258-4eac-be24-3fba916c6ad3","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/13c01281-c258-4eac-be24-3fba916c6ad3","pdf_url":"https://pure.tue.nl/ws/files/370336232/Contrastive_Learning_of_General-Purpose_Audio_Representations.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Saeed, A, Grangier, D & Zeghidour, N 2021, Contrastive learning of general-purpose audio representations. in ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)., 9413528, Institute of Electrical and Electronics Engineers, pp. 3875-3879, 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021, Virtual, Toronto, Canada, 6/06/21. https://doi.org/10.1109/ICASSP39728.2021.9413528","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:3093563057","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.10915.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"doi:10.48550/arxiv.2010.10915","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.10915","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/6cjk-8q79","is_oa":true,"landing_page_url":"https://doi.org/10.17023/6cjk-8q79","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"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":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.10915","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.10915","pdf_url":"https://arxiv.org/pdf/2010.10915","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3093563057.pdf","grobid_xml":"https://content.openalex.org/works/W3093563057.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W219040644","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2219249508","https://openalex.org/W2407127962","https://openalex.org/W2593116425","https://openalex.org/W2606176153","https://openalex.org/W2674088828","https://openalex.org/W2726515241","https://openalex.org/W2767754137","https://openalex.org/W2774571176","https://openalex.org/W2797583228","https://openalex.org/W2842511635","https://openalex.org/W2883595988","https://openalex.org/W2935542736","https://openalex.org/W2946948417","https://openalex.org/W2947454875","https://openalex.org/W2950577311","https://openalex.org/W2951292523","https://openalex.org/W2962960500","https://openalex.org/W2963341956","https://openalex.org/W2963571336","https://openalex.org/W2973157397","https://openalex.org/W2996383576","https://openalex.org/W3003382064","https://openalex.org/W3005680577","https://openalex.org/W3006926732","https://openalex.org/W3015949486","https://openalex.org/W3016181583","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3036601975","https://openalex.org/W3099782249","https://openalex.org/W3102342027","https://openalex.org/W3115293622","https://openalex.org/W3144810982","https://openalex.org/W3210683364","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6688816777","https://openalex.org/W6736723571","https://openalex.org/W6746570019","https://openalex.org/W6750591037","https://openalex.org/W6750665317","https://openalex.org/W6755207826","https://openalex.org/W6762718338","https://openalex.org/W6764266060","https://openalex.org/W6769196770","https://openalex.org/W6774314701","https://openalex.org/W6775634482","https://openalex.org/W6779326418","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6780483730","https://openalex.org/W6803949091","https://openalex.org/W6840487619","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2842511635","https://openalex.org/W3035524453","https://openalex.org/W2194775991","https://openalex.org/W3005680577","https://openalex.org/W2593116425","https://openalex.org/W3104805957","https://openalex.org/W3206649123","https://openalex.org/W3157916917","https://openalex.org/W3114632476","https://openalex.org/W3006926732","https://openalex.org/W2767754137","https://openalex.org/W3130223764","https://openalex.org/W3015949486","https://openalex.org/W3094454579","https://openalex.org/W3036968235","https://openalex.org/W3160262112","https://openalex.org/W3162133897","https://openalex.org/W3158388938","https://openalex.org/W2939574508","https://openalex.org/W2890052321"],"abstract_inverted_index":{"We":[0,46,71,96,109],"introduce":[1],"COLA,":[2],"a":[3,9,23,64,121],"self-supervised":[4,67,107],"pre-training":[5],"approach":[6,15],"for":[7,56],"learning":[8,55,61],"general-purpose":[10],"representation":[11,24],"of":[12,50,69],"audio.":[13,70],"Our":[14],"is":[16],"based":[17],"on":[18,48,74],"contrastive":[19,54],"learning:":[20],"it":[21],"learns":[22],"which":[25],"assigns":[26],"high":[27],"similarity":[28,40],"to":[29,41,62,83,114],"audio":[30],"segments":[31,42],"extracted":[32],"from":[33,43],"the":[34,75],"same":[35],"recording":[36],"while":[37],"assigning":[38],"lower":[39],"different":[44],"recordings.":[45],"build":[47],"top":[49],"recent":[51],"advances":[52],"in":[53],"computer":[57],"vision":[58],"and":[59,79,93,119,124],"reinforcement":[60],"design":[63,117],"lightweight,":[65],"easy-to-implement":[66],"model":[68],"pre-train":[72,123],"embeddings":[73],"large-scale":[76],"Audioset":[77],"database":[78],"transfer":[80],"these":[81],"representations":[82],"9":[84],"diverse":[85],"classification":[86],"tasks,":[87],"including":[88],"speech,":[89],"music,":[90],"animal":[91],"sounds,":[92],"acoustic":[94],"scenes.":[95],"show":[97],"that":[98],"despite":[99],"its":[100],"simplicity,":[101],"our":[102],"method":[103],"significantly":[104],"outperforms":[105],"previous":[106],"systems.":[108],"furthermore":[110],"conduct":[111],"ablation":[112],"studies":[113],"identify":[115],"key":[116],"choices":[118],"release":[120],"library1to":[122],"fine-tune":[125],"COLA":[126],"models.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":16}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}