{"id":"https://openalex.org/W4394862910","doi":"https://doi.org/10.1109/taslp.2024.3389631","title":"A Large-Scale Evaluation of Speech Foundation Models","display_name":"A Large-Scale Evaluation of Speech Foundation Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394862910","doi":"https://doi.org/10.1109/taslp.2024.3389631"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3389631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3389631","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078976109","display_name":"Heng-Jui Chang","orcid":"https://orcid.org/0000-0002-1690-2610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng-Jui Chang","raw_affiliation_strings":["CSAIL, MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"CSAIL, MIT, Cambridge, MA, USA","institution_ids":[]}]},{"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":["CLSP, JHU, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"CLSP, JHU, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"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":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, 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 Lai","raw_affiliation_strings":["CSAIL, MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"CSAIL, MIT, Cambridge, MA, USA","institution_ids":[]}]},{"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":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, 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/I4210098776","display_name":"Lawrie Technology (United States)","ror":"https://ror.org/00xky7n51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["LTI, CMU, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"LTI, CMU, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210098776"]}]},{"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/I4210098776","display_name":"Lawrie Technology (United States)","ror":"https://ror.org/00xky7n51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["LTI, CMU, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"LTI, CMU, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210098776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054413049","display_name":"Hsiang-Sheng Tsai","orcid":"https://orcid.org/0009-0008-2574-1610"},"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":"Hsiang-Sheng Tsai","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036438005","display_name":"Tzu-hsun Feng","orcid":"https://orcid.org/0009-0005-1993-6161"},"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-hsun Feng","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, 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":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"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":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, 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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yung-Sung Chuang","raw_affiliation_strings":["CSAIL, MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"CSAIL, MIT, Cambridge, MA, USA","institution_ids":[]}]},{"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":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, 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":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050838145","display_name":"Kushal Lakhotia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kushal Lakhotia","raw_affiliation_strings":["FAIR, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"FAIR, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336"]}]},{"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, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Amazon AI, New York, NY, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103742478","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdelrahman Mohamed","raw_affiliation_strings":["FAIR, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"FAIR, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336"]}]},{"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/I4210098776","display_name":"Lawrie Technology (United States)","ror":"https://ror.org/00xky7n51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["LTI, CMU, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"LTI, CMU, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210098776"]}]},{"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":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":21,"corresponding_author_ids":["https://openalex.org/A5078898845"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":12.7115,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.98948653,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"2884","last_page":"2899"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.7324991226196289},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6267046332359314},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49109530448913574},{"id":"https://openalex.org/keywords/scale-model","display_name":"Scale model","score":0.4167368412017822},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3882451355457306},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.25778642296791077},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.1667809784412384},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.13650202751159668},{"id":"https://openalex.org/keywords/aerospace-engineering","display_name":"Aerospace engineering","score":0.13020578026771545},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.09001141786575317},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.0818105936050415}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7324991226196289},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6267046332359314},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49109530448913574},{"id":"https://openalex.org/C152588345","wikidata":"https://www.wikidata.org/wiki/Q6498959","display_name":"Scale model","level":2,"score":0.4167368412017822},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3882451355457306},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25778642296791077},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.1667809784412384},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13650202751159668},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.13020578026771545},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.09001141786575317},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0818105936050415}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3389631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3389631","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.4099999964237213,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":115,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1567520911","https://openalex.org/W1586176709","https://openalex.org/W1635512741","https://openalex.org/W2094721231","https://openalex.org/W2107092366","https://openalex.org/W2127141656","https://openalex.org/W2146334809","https://openalex.org/W2219249508","https://openalex.org/W2460742184","https://openalex.org/W2532494225","https://openalex.org/W2696967604","https://openalex.org/W2734774145","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2804935296","https://openalex.org/W2889329491","https://openalex.org/W2890964092","https://openalex.org/W2896457183","https://openalex.org/W2917128112","https://openalex.org/W2923014074","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2952218014","https://openalex.org/W2962739339","https://openalex.org/W2962866211","https://openalex.org/W2962896155","https://openalex.org/W2963532001","https://openalex.org/W2963745998","https://openalex.org/W2964243274","https://openalex.org/W2965373594","https://openalex.org/W2972541922","https://openalex.org/W2972584841","https://openalex.org/W2972943112","https://openalex.org/W2972949456","https://openalex.org/W2973049979","https://openalex.org/W2977838803","https://openalex.org/W2981087920","https://openalex.org/W2982223350","https://openalex.org/W3015213852","https://openalex.org/W3015265920","https://openalex.org/W3016181583","https://openalex.org/W3027008958","https://openalex.org/W3041561163","https://openalex.org/W3096338464","https://openalex.org/W3097286738","https://openalex.org/W3098598562","https://openalex.org/W3099330747","https://openalex.org/W3103152812","https://openalex.org/W3119913666","https://openalex.org/W3148040514","https://openalex.org/W3161223924","https://openalex.org/W3162313915","https://openalex.org/W3173767661","https://openalex.org/W3189296823","https://openalex.org/W3195577433","https://openalex.org/W3197223534","https://openalex.org/W3197580070","https://openalex.org/W3198858531","https://openalex.org/W3203140070","https://openalex.org/W3206252155","https://openalex.org/W3206495532","https://openalex.org/W3207300132","https://openalex.org/W3208743843","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211224152","https://openalex.org/W4221161768","https://openalex.org/W4224821750","https://openalex.org/W4226103796","https://openalex.org/W4226380987","https://openalex.org/W4285250921","https://openalex.org/W4289750118","https://openalex.org/W4296068815","https://openalex.org/W4297683418","https://openalex.org/W4297808394","https://openalex.org/W4319862416","https://openalex.org/W4319862442","https://openalex.org/W4319862635","https://openalex.org/W4375869040","https://openalex.org/W4375869259","https://openalex.org/W4378470126","https://openalex.org/W4385571440","https://openalex.org/W4385822439","https://openalex.org/W4385822668","https://openalex.org/W4385822952","https://openalex.org/W4385823182","https://openalex.org/W4390912371","https://openalex.org/W6608792757","https://openalex.org/W6636611734","https://openalex.org/W6688816777","https://openalex.org/W6751425476","https://openalex.org/W6753575415","https://openalex.org/W6759393636","https://openalex.org/W6762533536","https://openalex.org/W6766673545","https://openalex.org/W6771467084","https://openalex.org/W6777776875","https://openalex.org/W6780218876","https://openalex.org/W6780680273","https://openalex.org/W6783867762","https://openalex.org/W6785772365","https://openalex.org/W6786696081","https://openalex.org/W6800751262","https://openalex.org/W6803378298","https://openalex.org/W6809593508","https://openalex.org/W6810007534","https://openalex.org/W6839738141","https://openalex.org/W6840412704","https://openalex.org/W6843036773","https://openalex.org/W6844194202","https://openalex.org/W6844662008","https://openalex.org/W6847363464","https://openalex.org/W6852781585"],"related_works":["https://openalex.org/W4311518154","https://openalex.org/W1964996159","https://openalex.org/W4248167041","https://openalex.org/W4255785186","https://openalex.org/W2316285465","https://openalex.org/W2317286081","https://openalex.org/W343220070","https://openalex.org/W2321942072","https://openalex.org/W1996215946","https://openalex.org/W2036196817"],"abstract_inverted_index":{"The":[0],"foundation":[1,7,71,121,147,172],"model":[2,8,122,148],"paradigm":[3,49],"leverages":[4],"a":[5,43,74,94,106,159],"shared":[6],"to":[9,46,69,163],"achieve":[10],"state-of-the-art":[11],"(SOTA)":[12],"performance":[13],"for":[14,110],"various":[15],"tasks,":[16,80],"requiring":[17],"minimal":[18],"downstream-specific":[19],"data":[20],"collection":[21],"and":[22,90,170,182,186],"modeling.":[23],"This":[24],"approach":[25],"has":[26],"proven":[27],"crucial":[28],"in":[29,100,116],"the":[30,38,48,57,82,112,119,138,145,180,183,189],"field":[31],"of":[32,77,84,161,168,188],"Natural":[33],"Language":[34],"Processing":[35],"(NLP).":[36],"However,":[37],"speech":[39,78,113,171],"processing":[40,59,79,114],"community":[41,133],"lacks":[42],"similar":[44],"setup":[45],"explore":[47],"systematically.":[50],"To":[51],"bridge":[52],"this":[53],"gap,":[54],"we":[55,135,157],"establish":[56],"Speech":[58],"Universal":[60],"PERformance":[61],"Benchmark":[62],"(SUPERB).":[63],"SUPERB":[64,117,154,169],"represents":[65],"an":[66,87,165],"ecosystem":[67],"designed":[68],"evaluate":[70],"models":[72,181],"across":[73,152,177],"wide":[75],"range":[76],"facilitating":[81],"sharing":[83],"results":[85,131],"on":[86],"online":[88],"leaderboard":[89],"fostering":[91],"collaboration":[92],"through":[93],"community-driven":[95],"benchmark":[96],"database":[97],"that":[98,137],"aids":[99],"new":[101],"development":[102],"cycles.":[103],"We":[104],"present":[105],"unified":[107],"learning":[108],"framework":[109,139],"solving":[111],"tasks":[115,178],"with":[118,132],"frozen":[120],"followed":[123],"by":[124],"task-specialized":[125],"lightweight":[126],"prediction":[127],"heads.":[128],"Combining":[129],"our":[130],"submissions,":[134],"verify":[136],"is":[140],"simple":[141],"yet":[142],"effective,":[143],"as":[144],"best-performing":[146],"shows":[149],"competitive":[150],"generalizability":[151],"most":[153],"tasks.":[155],"Finally,":[156],"conduct":[158],"series":[160],"analyses":[162],"offer":[164],"in-depth":[166],"understanding":[167],"models,":[173],"including":[174],"information":[175],"flows":[176],"inside":[179],"statistical":[184],"significance":[185],"robustness":[187],"benchmark.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2025-10-10T00:00:00"}