{"id":"https://openalex.org/W4392910434","doi":"https://doi.org/10.1109/icassp48485.2024.10445941","title":"AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models","display_name":"AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910434","doi":"https://doi.org/10.1109/icassp48485.2024.10445941"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445941","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":"article","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":null,"display_name":"Yuan Tseng","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan Tseng","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084236961","display_name":"Layne Berry","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Layne Berry","raw_affiliation_strings":["University of Texas at Austin,USA","University of Texas at Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100586631","display_name":"Yi-Ting Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Ting Chen","raw_affiliation_strings":["Academia Sinica,Taiwan","Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104260175","display_name":"I-Hsiang Chiu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"I-Hsiang Chiu","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112525249","display_name":"Hsuan-Hao Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsuan-Hao Lin","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103127114","display_name":"Max Liu","orcid":"https://orcid.org/0000-0002-3553-7380"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Max Liu","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075735963","display_name":"Puyuan Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Puyuan Peng","raw_affiliation_strings":["University of Texas at Austin,USA","University of Texas at Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053466746","display_name":"Yi-Jen Shih","orcid":"https://orcid.org/0000-0003-3481-3117"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Jen Shih","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102989258","display_name":"Hung\u2010Yu Wang","orcid":"https://orcid.org/0000-0001-5935-8638"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yu Wang","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101474128","display_name":"Haibin Wu","orcid":"https://orcid.org/0000-0001-7166-5534"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Haibin Wu","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063149046","display_name":"Po-Yao Huang","orcid":"https://orcid.org/0000-0002-3319-5145"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Po-Yao Huang","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069644229","display_name":"Chun-Mao Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Mao Lai","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029566548","display_name":"Shang-Wen Li","orcid":"https://orcid.org/0000-0003-0656-9874"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang-Wen Li","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004717608","display_name":"David Harwath","orcid":"https://orcid.org/0000-0003-0206-0253"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Harwath","raw_affiliation_strings":["University of Texas at Austin,USA","University of Texas at Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica,Taiwan","Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103742478","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdelrahman Mohamed","raw_affiliation_strings":["Rembrand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rembrand","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046324698","display_name":"Chi-Luen Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Luen Feng","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":18,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9744,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.9438232,"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":"6890","last_page":"6894"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9735999703407288,"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":0.9690999984741211,"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":0.8170523047447205},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8000586032867432},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7063170671463013},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6777321100234985},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5930901765823364},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4229540228843689},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40957915782928467},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.23564869165420532},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06451046466827393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8170523047447205},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8000586032867432},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7063170671463013},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6777321100234985},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5930901765823364},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4229540228843689},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40957915782928467},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.23564869165420532},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06451046466827393},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445941","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2073227393","https://openalex.org/W2096391593","https://openalex.org/W2551572271","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2619947201","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2884739346","https://openalex.org/W2891205112","https://openalex.org/W2963121782","https://openalex.org/W3015371781","https://openalex.org/W3015734344","https://openalex.org/W3094502228","https://openalex.org/W3170837227","https://openalex.org/W3197580070","https://openalex.org/W3201143670","https://openalex.org/W3205786327","https://openalex.org/W3207758636","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4214718130","https://openalex.org/W4226380987","https://openalex.org/W4285250921","https://openalex.org/W4312365371","https://openalex.org/W4313156423","https://openalex.org/W4319862442","https://openalex.org/W4322614701","https://openalex.org/W6600983433","https://openalex.org/W6729831399","https://openalex.org/W6754048563","https://openalex.org/W6754420807","https://openalex.org/W6755862295","https://openalex.org/W6770805772","https://openalex.org/W6780218876","https://openalex.org/W6787473416","https://openalex.org/W6795711426","https://openalex.org/W6797781246","https://openalex.org/W6809947431","https://openalex.org/W6810168380","https://openalex.org/W6840200333","https://openalex.org/W6843825870","https://openalex.org/W6847495150","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2271369634","https://openalex.org/W2130974462","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W2028665553","https://openalex.org/W2086519370"],"abstract_inverted_index":{"Audio-visual":[0],"representation":[1],"learning":[2],"aims":[3],"to":[4,82,138],"develop":[5],"systems":[6],"with":[7,105,112,124],"human-like":[8],"perception":[9],"by":[10],"utilizing":[11],"correlation":[12],"between":[13],"auditory":[14],"and":[15,29,52,65,74,108,130],"visual":[16],"information.":[17],"However,":[18],"current":[19],"models":[20,73,80],"often":[21],"focus":[22],"on":[23,56,91],"a":[24,116,131],"limited":[25],"set":[26],"of":[27,32,49,78],"tasks,":[28,84],"generalization":[30],"abilities":[31],"learned":[33],"representations":[34,55,101],"are":[35],"unclear.":[36],"To":[37],"this":[38],"end,":[39],"we":[40,98],"propose":[41],"the":[42,86],"AV-SUPERB":[43],"benchmark":[44,123],"that":[45,76,100],"enables":[46],"general-purpose":[47],"evaluation":[48,125],"unimodal":[50],"audio/visual":[51],"bimodal":[53],"fusion":[54],"7":[57],"datasets":[58],"covering":[59],"5":[60,70],"audio-visual":[61,143],"tasks":[62],"in":[63,142],"speech":[64],"audio":[66,109],"processing.":[67],"We":[68,120],"evaluate":[69],"recent":[71],"self-supervised":[72],"show":[75,99],"none":[77],"these":[79],"generalize":[81],"all":[83],"emphasizing":[85],"need":[87],"for":[88],"future":[89],"study":[90],"improving":[92],"universal":[93],"model":[94,132],"performance.":[95],"In":[96],"addition,":[97],"may":[102],"be":[103],"improved":[104],"intermediate-task":[106],"fine-tuning":[107],"event":[110],"classification":[111],"AudioSet":[113],"serves":[114],"as":[115],"strong":[117],"intermediate":[118],"task.":[119],"release":[121],"our":[122],"code":[126],"<sup":[127,135],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[128,136],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[129],"submission":[133],"platform":[134],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[137],"encourage":[139],"further":[140],"research":[141],"learning.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
