{"id":"https://openalex.org/W3197580070","doi":"https://doi.org/10.21437/interspeech.2021-1775","title":"SUPERB: Speech Processing Universal PERformance Benchmark","display_name":"SUPERB: Speech Processing Universal PERformance Benchmark","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197580070","doi":"https://doi.org/10.21437/interspeech.2021-1775","mag":"3197580070"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1775","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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":"https://openalex.org/A5078898845","display_name":"Shu-Wen Yang","orcid":"https://orcid.org/0000-0001-5503-9410"},"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":true,"raw_author_name":"Shu-wen Yang","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069156649","display_name":"Po-Han Chi","orcid":"https://orcid.org/0000-0001-8183-3781"},"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":"Po-Han Chi","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058729228","display_name":"Yung-Sung Chuang","orcid":"https://orcid.org/0000-0002-1723-5063"},"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":"Yung-Sung Chuang","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010825170","display_name":"Cheng-I Lai","orcid":"https://orcid.org/0000-0002-2343-8596"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng-I Jeff Lai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050838145","display_name":"Kushal Lakhotia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kushal Lakhotia","raw_affiliation_strings":["Facebook AI Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047521320","display_name":"Yist Y. Lin","orcid":"https://orcid.org/0009-0000-9054-1596"},"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":"Yist Y. Lin","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018050919","display_name":"Andy T. Liu","orcid":"https://orcid.org/0000-0002-2502-3992"},"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":"Andy T. Liu","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108124525","display_name":"Guan-Ting 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":"Guan-Ting Lin","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100878484","display_name":"Tzu-Hsien Huang","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":"Tzu-Hsien Huang","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078942855","display_name":"Wei-Cheng 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":"Wei-Cheng Tseng","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049152361","display_name":"Ko-tik Lee","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":"Ko-tik Lee","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084868332","display_name":"Da-Rong Liu","orcid":"https://orcid.org/0009-0005-0090-7408"},"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":"Da-Rong Liu","raw_affiliation_strings":["National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101619225","display_name":"Zili Huang","orcid":"https://orcid.org/0000-0003-1238-8017"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zili Huang","raw_affiliation_strings":["Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032243328","display_name":"Shuyan Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuyan Dong","raw_affiliation_strings":["Amazon AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029566548","display_name":"Shang-Wen Li","orcid":"https://orcid.org/0000-0003-0656-9874"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shang-Wen Li","raw_affiliation_strings":["Amazon AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103742478","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdelrahman Mohamed","raw_affiliation_strings":["Facebook AI Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":20,"corresponding_author_ids":["https://openalex.org/A5078898845"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":66.615,"has_fulltext":false,"cited_by_count":633,"citation_normalized_percentile":{"value":0.99939191,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1194","last_page":"1198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.996399998664856,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9955999851226807,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9900000095367432,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7882404327392578},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7827718257904053},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5210330486297607},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49530234932899475}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7882404327392578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827718257904053},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5210330486297607},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49530234932899475},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1775","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2134800885","https://openalex.org/W2146334809","https://openalex.org/W2294718077","https://openalex.org/W2883725317","https://openalex.org/W2890964092","https://openalex.org/W2896457183","https://openalex.org/W2923014074","https://openalex.org/W2953190524","https://openalex.org/W2962739339","https://openalex.org/W2972382840","https://openalex.org/W2972584841","https://openalex.org/W2972943112","https://openalex.org/W2972949456","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2979476256","https://openalex.org/W2981087920","https://openalex.org/W2982223350","https://openalex.org/W2990873191","https://openalex.org/W3006926732","https://openalex.org/W3015213852","https://openalex.org/W3016181583","https://openalex.org/W3027008958","https://openalex.org/W3034238904","https://openalex.org/W3035164673","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3097286738","https://openalex.org/W3099944122","https://openalex.org/W3112034174","https://openalex.org/W3161223924","https://openalex.org/W3161627112","https://openalex.org/W3198858531","https://openalex.org/W3209059054","https://openalex.org/W4287553982","https://openalex.org/W4287591426","https://openalex.org/W4297683418","https://openalex.org/W4297808394","https://openalex.org/W4298277274"],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W2150288981","https://openalex.org/W1599055764","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2131711534","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351","https://openalex.org/W2099105119"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,118,168],"(SSL)":[2],"has":[3],"proven":[4],"vital":[5],"for":[6,33,105],"advancing":[7],"research":[8,165],"in":[9,166],"natural":[10],"language":[11],"processing":[12,41,58,80],"(NLP)":[13],"and":[14,29,86,143,157,169],"computer":[15],"vision":[16],"(CV).The":[17],"paradigm":[18],"pretrains":[19],"a":[20,44,64,71,75,110,151,154,158],"shared":[21,72,93,128],"model":[22,73],"on":[23,98,123],"large":[24],"volumes":[25],"of":[26,70,78,91,125],"unlabeled":[27],"data":[28],"achieves":[30],"state-of-the-art":[31],"(SOTA)":[32],"various":[34],"tasks":[35,81,116],"with":[36,82,153],"minimal":[37,83],"adaptation.However,":[38],"the":[39,50,68,92,100,126,133,164],"speech":[40,79,171],"community":[42],"lacks":[43],"similar":[45],"setup":[46],"to":[47,66,113,162],"systematically":[48],"explore":[49],"paradigm.To":[51],"bridge":[52],"this":[53],"gap,":[54],"we":[55,95],"introduce":[56],"Speech":[57],"Universal":[59],"PERformance":[60],"Benchmark":[61],"(SUPERB).SUPERB":[62],"is":[63,135],"leaderboard":[65,155],"benchmark":[67,159],"performance":[69],"across":[74,145],"wide":[76],"range":[77],"architecture":[84],"changes":[85],"labeled":[87],"data.Among":[88],"multiple":[89],"usages":[90],"model,":[94],"especially":[96],"focus":[97],"extracting":[99],"representation":[101,167],"learned":[102],"from":[103],"SSL":[104,138],"its":[106],"preferable":[107],"re-usability.We":[108],"present":[109],"simple":[111],"framework":[112,134],"solve":[114],"SUPERB":[115,146,149],"by":[117],"task-specialized":[119],"lightweight":[120],"prediction":[121],"heads":[122],"top":[124],"frozen":[127],"model.Our":[129],"results":[130],"demonstrate":[131],"that":[132],"promising":[136],"as":[137,150],"representations":[139],"show":[140],"competitive":[141],"generalizability":[142],"accessibility":[144],"tasks.We":[147],"release":[148],"challenge":[152],"1":[156],"toolkit":[160],"2":[161],"fuel":[163],"general":[170],"processing.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":25},{"year":2025,"cited_by_count":132},{"year":2024,"cited_by_count":151},{"year":2023,"cited_by_count":210},{"year":2022,"cited_by_count":109},{"year":2021,"cited_by_count":6}],"updated_date":"2026-05-30T09:04:40.226872","created_date":"2025-10-10T00:00:00"}
