{"id":"https://openalex.org/W4372266552","doi":"https://doi.org/10.1109/icassp49357.2023.10095889","title":"CLAP Learning Audio Concepts from Natural Language Supervision","display_name":"CLAP Learning Audio Concepts from Natural Language Supervision","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266552","doi":"https://doi.org/10.1109/icassp49357.2023.10095889"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073250019","display_name":"Benjamin Elizalde","orcid":"https://orcid.org/0000-0001-6461-5790"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Benjamin Elizalde","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017946811","display_name":"Soham Deshmukh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Soham Deshmukh","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067360890","display_name":"Mahmoud Al Ismail","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mahmoud Al Ismail","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101528069","display_name":"Huaming Wang","orcid":"https://orcid.org/0000-0002-4434-7482"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huaming Wang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":95.6021,"has_fulltext":false,"cited_by_count":400,"citation_normalized_percentile":{"value":0.99964855,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9993000030517578,"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":0.9965999722480774,"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":0.8206873536109924},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4939277768135071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4933399260044098},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49043676257133484},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.488357275724411},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46190792322158813},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4275561571121216},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2500761151313782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8206873536109924},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4939277768135071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4933399260044098},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49043676257133484},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.488357275724411},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46190792322158813},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4275561571121216},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2500761151313782},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2046972719","https://openalex.org/W2938440247","https://openalex.org/W2979826702","https://openalex.org/W3015591594","https://openalex.org/W3036601975","https://openalex.org/W3049446265","https://openalex.org/W3094550259","https://openalex.org/W3138521398","https://openalex.org/W3162331882","https://openalex.org/W3166396011","https://openalex.org/W3176445421","https://openalex.org/W3196496149","https://openalex.org/W3204696009","https://openalex.org/W3205475937","https://openalex.org/W3209984917","https://openalex.org/W3213454282","https://openalex.org/W3215626407","https://openalex.org/W4205633160","https://openalex.org/W4205689591","https://openalex.org/W4221150524","https://openalex.org/W4225299287","https://openalex.org/W4284898017","https://openalex.org/W6780218876","https://openalex.org/W6791353385","https://openalex.org/W6802510933","https://openalex.org/W6803872405","https://openalex.org/W6809947431"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4205302943","https://openalex.org/W2119949815","https://openalex.org/W2561132942","https://openalex.org/W2142795561","https://openalex.org/W3155418658","https://openalex.org/W2379948177","https://openalex.org/W2354332708"],"abstract_inverted_index":{"Mainstream":[0],"machine":[1],"listening":[2],"models":[3,33],"are":[4],"trained":[5,92],"to":[6,17,51],"learn":[7,52],"audio":[8,38,53,71,82,96,131],"concepts":[9,54],"under":[10,25],"the":[11,30,45,148],"paradigm":[12],"of":[13,32,113,150],"one":[14,22],"class":[15,153,158],"label":[16],"many":[18],"recordings":[19],"focusing":[20],"on":[21,103],"task.":[23],"Learning":[24],"such":[26,110],"restricted":[27],"supervision":[28],"limits":[29],"flexibility":[31],"because":[34],"they":[35],"require":[36],"labeled":[37,154],"for":[39],"training":[40,151],"and":[41,70,76,83,97,100,118,138,163],"can":[42],"only":[43],"predict":[44],"predefined":[46],"categories.":[47],"Instead,":[48],"we":[49,128],"propose":[50],"from":[55],"natural":[56],"language":[57,69],"supervision.":[58],"We":[59,91],"call":[60],"our":[61],"approach":[62],"Contrastive":[63],"Language-Audio":[64],"Pretraining":[65],"(CLAP),":[66],"which":[67],"connects":[68],"by":[72],"using":[73],"two":[74],"encoders":[75],"a":[77,87,134],"contrastive":[78],"learning":[79,136],"objective,":[80],"bringing":[81],"text":[84,98],"descriptions":[85],"into":[86],"joint":[88],"multimodal":[89],"space.":[90],"CLAP":[93,120],"with":[94,152],"128k":[95],"pairs":[99],"evaluated":[101,129],"it":[102],"16":[104],"downstream":[105,168],"tasks":[106],"across":[107],"7":[108],"domains,":[109],"as":[111],"classification":[112],"sound":[114],"events,":[115],"scenes,":[116],"music,":[117],"speech.":[119],"establishes":[121],"state-of-the-art":[122],"(SoTA)":[123],"in":[124,133,141,166],"Zero-Shot":[125,145],"performance.":[126],"Also,":[127],"CLAP\u2019s":[130],"encoder":[132],"supervised":[135],"setup":[137],"achieved":[139],"SoTA":[140],"5":[142],"tasks.":[143,169],"The":[144],"capability":[146],"removes":[147],"need":[149],"audio,":[155],"enables":[156],"flexible":[157],"prediction":[159],"at":[160],"inference":[161],"time,":[162],"generalizes":[164],"well":[165],"multiple":[167],"Code":[170],"is":[171],"available":[172],"at:":[173],"https://github.com/microsoft/CLAP.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":85},{"year":2025,"cited_by_count":176},{"year":2024,"cited_by_count":106},{"year":2023,"cited_by_count":30},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-02T14:50:37.381335","created_date":"2025-10-10T00:00:00"}
