{"id":"https://openalex.org/W4392903801","doi":"https://doi.org/10.1109/icassp48485.2024.10448504","title":"Natural Language Supervision For General-Purpose Audio Representations","display_name":"Natural Language Supervision For General-Purpose Audio Representations","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903801","doi":"https://doi.org/10.1109/icassp48485.2024.10448504"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":"last","author":{"id":"https://openalex.org/A5101528071","display_name":"Huaming Wang","orcid":"https://orcid.org/0000-0003-1490-2673"},"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":22.5261,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.99734206,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"336","last_page":"340"},"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":0.9977999925613403,"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":0.9975000023841858,"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":0.8285067081451416},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6010009050369263},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5732540488243103},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5451412200927734},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5371482968330383},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.532461941242218},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.501969575881958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4991583824157715},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.441991925239563},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43238332867622375},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.42849472165107727},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4144763946533203},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4106071889400482},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.33695805072784424},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.27229201793670654},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.25795069336891174},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10584479570388794}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8285067081451416},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6010009050369263},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5732540488243103},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5451412200927734},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5371482968330383},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.532461941242218},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.501969575881958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4991583824157715},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.441991925239563},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43238332867622375},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.42849472165107727},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4144763946533203},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4106071889400482},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.33695805072784424},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.27229201793670654},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25795069336891174},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10584479570388794},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/icassp48485.2024.10448504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2465534249","https://openalex.org/W2593116425","https://openalex.org/W2742542661","https://openalex.org/W2883409523","https://openalex.org/W2961193895","https://openalex.org/W2963686995","https://openalex.org/W3015591594","https://openalex.org/W3162331882","https://openalex.org/W3176445421","https://openalex.org/W3207758636","https://openalex.org/W4205689591","https://openalex.org/W4210913346","https://openalex.org/W4221150524","https://openalex.org/W4226442948","https://openalex.org/W4284898017","https://openalex.org/W4312097006","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4372340819","https://openalex.org/W4377372369","https://openalex.org/W4385822467","https://openalex.org/W4400033239","https://openalex.org/W6719667659","https://openalex.org/W6732646663","https://openalex.org/W6736723571","https://openalex.org/W6809947431","https://openalex.org/W6852818750","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2109142991","https://openalex.org/W1911859126","https://openalex.org/W46679383","https://openalex.org/W2350061705","https://openalex.org/W2040013831","https://openalex.org/W1611900921","https://openalex.org/W2112616324","https://openalex.org/W2064012922","https://openalex.org/W2106826515","https://openalex.org/W2717715803"],"abstract_inverted_index":{"Audio-Language":[0],"models":[1,37,176],"jointly":[2],"learn":[3,79,101],"multimodal":[4,127],"text":[5],"and":[6,25,34,119,177],"audio":[7,80,85,89,118,183],"representations":[8,21,121,152],"that":[9,60],"enable":[10],"Zero-Shot":[11,76],"inference.":[12,77],"Models":[13],"rely":[14],"on":[15,87,153,187],"the":[16,23,93,112,117,138,148,157,160,167,179],"encoders":[17,74,135],"to":[18,27,136],"create":[19],"powerful":[20],"of":[22,67,92,96,111,150,166],"input":[24],"generalize":[26],"multiple":[28],"tasks":[29,172],"ranging":[30],"from":[31],"sounds,":[32],"music,":[33],"speech.":[35],"Although":[36],"have":[38],"achieved":[39],"remarkable":[40],"performance,":[41],"there":[42],"is":[43,61,186],"still":[44],"a":[45,55,64,125,142],"gap":[46],"with":[47,63],"task-specific":[48],"models.":[49,115],"In":[50],"this":[51],"paper,":[52],"we":[53,82,104],"propose":[54],"Contrastive":[56,130],"Language-Audio":[57],"Pretraining":[58],"model":[59,109,163],"pretrained":[62],"diverse":[65],"collection":[66],"4.6M":[68],"audio-text":[69],"pairs":[70],"employing":[71],"two":[72],"innovative":[73],"for":[75],"To":[78,100],"representations,":[81,103],"trained":[83,105],"an":[84,106],"encoder":[86],"22":[88],"tasks,":[90,156],"instead":[91,110],"standard":[94,113],"training":[95],"sound":[97],"event":[98],"classification.":[99],"language":[102,120],"autoregressive":[107],"decoder-only":[108],"encoder-only":[114],"Then,":[116],"are":[122],"brought":[123],"into":[124],"joint":[126],"space":[128],"using":[129],"Learning.":[131],"We":[132,145],"used":[133],"our":[134,151],"improve":[137],"downstream":[139,155],"performance":[140],"by":[141],"large":[143],"margin.":[144],"extensively":[146],"evaluated":[147],"generalization":[149],"26":[154],"largest":[158],"in":[159,170],"literature.":[161],"Our":[162],"achieves":[164],"state":[165],"art":[168],"results":[169],"several":[171],"outperforming":[173],"4":[174],"different":[175],"leading":[178],"way":[180],"towards":[181],"general-purpose":[182],"representations.":[184],"Code":[185],"GitHub1.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":31},{"year":2024,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}