{"id":"https://openalex.org/W4372260310","doi":"https://doi.org/10.1109/icassp49357.2023.10095969","title":"Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","display_name":"Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260310","doi":"https://doi.org/10.1109/icassp49357.2023.10095969"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095969","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":true,"oa_status":"green","oa_url":"https://hal.science/hal-04766539/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102132394","display_name":"Yusong Wu","orcid":"https://orcid.org/0000-0003-4190-974X"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yusong Wu","raw_affiliation_strings":["Universit&#x00E9; de Montr&#x00E9;al,Mila, Quebec Artificial Intelligence Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; de Montr&#x00E9;al,Mila, Quebec Artificial Intelligence Institute","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451980","display_name":"Ke Chen","orcid":"https://orcid.org/0000-0001-8357-3741"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425864","display_name":"Tianyu Zhang","orcid":"https://orcid.org/0000-0003-1969-2855"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tianyu Zhang","raw_affiliation_strings":["Universit&#x00E9; de Montr&#x00E9;al,Mila, Quebec Artificial Intelligence Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; de Montr&#x00E9;al,Mila, Quebec Artificial Intelligence Institute","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103129849","display_name":"Yuchen Hui","orcid":"https://orcid.org/0000-0002-9659-3714"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yuchen Hui","raw_affiliation_strings":["Universit&#x00E9; de Montr&#x00E9;al,Mila, Quebec Artificial Intelligence Institute","LAION"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; de Montr&#x00E9;al,Mila, Quebec Artificial Intelligence Institute","institution_ids":["https://openalex.org/I4210164802"]},{"raw_affiliation_string":"LAION","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017455302","display_name":"Taylor Berg-Kirkpatrick","orcid":"https://orcid.org/0000-0002-1283-4075"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taylor Berg-Kirkpatrick","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042278809","display_name":"Shlomo Dubnov","orcid":"https://orcid.org/0000-0003-0222-1125"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shlomo Dubnov","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":397,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9975000023841858,"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":0.9955000281333923,"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":0.79413902759552},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6710751056671143},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5678661465644836},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5372419953346252},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.516165554523468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5155048966407776},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49686339497566223},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.46533316373825073},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45057258009910583},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.44267037510871887},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4169195294380188},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.20217680931091309},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.18874198198318481},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10673192143440247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79413902759552},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6710751056671143},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5678661465644836},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5372419953346252},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.516165554523468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5155048966407776},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49686339497566223},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.46533316373825073},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45057258009910583},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44267037510871887},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4169195294380188},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.20217680931091309},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.18874198198318481},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10673192143440247},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095969","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"},{"id":"pmh:oai:HAL:hal-04766539v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04766539","pdf_url":"https://hal.science/hal-04766539/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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2023, Rhodes Island, France. pp.1-5, &#x27E8;10.1109/ICASSP49357.2023.10095969&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04766539v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04766539","pdf_url":"https://hal.science/hal-04766539/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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2023, Rhodes Island, France. pp.1-5, &#x27E8;10.1109/ICASSP49357.2023.10095969&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4372260310.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2593116425","https://openalex.org/W2622263826","https://openalex.org/W2792643794","https://openalex.org/W2896457183","https://openalex.org/W2965373594","https://openalex.org/W3015371781","https://openalex.org/W3015591594","https://openalex.org/W3094550259","https://openalex.org/W3094897602","https://openalex.org/W3138516171","https://openalex.org/W3166396011","https://openalex.org/W3174906557","https://openalex.org/W3176445421","https://openalex.org/W3198452188","https://openalex.org/W3205475937","https://openalex.org/W4205689591","https://openalex.org/W4210913346","https://openalex.org/W4221157007","https://openalex.org/W4226442948","https://openalex.org/W4284898017","https://openalex.org/W4288089799","https://openalex.org/W4372266552","https://openalex.org/W4385822467","https://openalex.org/W6631190155","https://openalex.org/W6739622702","https://openalex.org/W6749029207","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6769627184","https://openalex.org/W6791353385","https://openalex.org/W6797613833","https://openalex.org/W6807957504","https://openalex.org/W6838439425","https://openalex.org/W6849549116"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W3037187668","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177"],"abstract_inverted_index":{"Contrastive":[0],"learning":[1],"has":[2],"shown":[3],"remarkable":[4],"success":[5],"in":[6,131,144,158],"the":[7,74,82,88,99,139,145,159,167,177],"field":[8],"of":[9,20,48,94],"multimodal":[10],"representation":[11,28],"learning.":[12],"In":[13,135],"this":[14,39],"paper,":[15],"we":[16,41,57,102],"propose":[17],"a":[18,45,59],"pipeline":[19],"contrastive":[21,60],"language-audio":[22,61],"pretraining":[23,62],"to":[24,85,90,106,151,155,176],"develop":[25],"an":[26],"audio":[27,31,67,92,116,120,136],"by":[29,64],"combining":[30],"data":[32,54],"with":[33],"natural":[34],"language":[35],"descriptions.":[36],"To":[37],"accomplish":[38],"target,":[40],"first":[42],"release":[43],"LAION-Audio-630K,":[44],"large":[46],"collection":[47],"633,526":[49],"audio-text":[50],"pairs":[51],"from":[52],"different":[53,66],"sources.":[55],"Second,":[56],"construct":[58],"model":[63,83,89,109,127,140,169],"considering":[65],"encoders":[68],"and":[69,78,97,118,148,166],"text":[70],"encoders.":[71],"We":[72],"incorporate":[73],"feature":[75],"fusion":[76],"mechanism":[77],"keyword-to-caption":[79],"augmentation":[80],"into":[81],"design":[84],"further":[86],"enable":[87],"process":[91],"inputs":[93],"variable":[95],"lengths":[96],"enhance":[98],"performance.":[100],"Third,":[101],"perform":[103],"comprehensive":[104],"experiments":[105],"evaluate":[107],"our":[108,126],"across":[110],"three":[111],"tasks:":[112],"text-to-audio":[113,132],"retrieval,":[114],"zero-shot":[115,146],"classification,":[117],"supervised":[119],"classification.":[121],"The":[122],"results":[123,157],"demonstrate":[124],"that":[125],"achieves":[128,141],"superior":[129],"performance":[130,143,153],"retrieval":[133],"task.":[134],"classification":[137],"tasks,":[138],"state-of-the-art":[142],"setting":[147],"is":[149],"able":[150],"obtain":[152],"comparable":[154],"models\u2019":[156],"non-zero-shot":[160],"setting.":[161],"LAION-Audio-630K":[162],"<sup":[163,170],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[164,171],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[165],"proposed":[168],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[172],"are":[173],"both":[174],"available":[175],"public.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":83},{"year":2025,"cited_by_count":191},{"year":2024,"cited_by_count":110},{"year":2023,"cited_by_count":13}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}
