{"id":"https://openalex.org/W3169320628","doi":"https://doi.org/10.1109/taslp.2021.3122291","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","display_name":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3169320628","doi":"https://doi.org/10.1109/taslp.2021.3122291","mag":"3169320628"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3122291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3122291","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.07447","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217"},"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":"Wei-Ning Hsu","raw_affiliation_strings":["Facebook Inc, 342996 New York, New York, United States, 10003 (e-mail: wnhsu@fb.com)","Facebook, Inc., New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-5546-5217","affiliations":[{"raw_affiliation_string":"Facebook Inc, 342996 New York, New York, United States, 10003 (e-mail: wnhsu@fb.com)","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113811530","display_name":"Benjamin Bolte","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"]},{"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":"Benjamin Bolte","raw_affiliation_strings":["Facebook AI Research, Menlo Park, California, United States, (e-mail: ben@bolte.cc)","[Facebook AI Research Menlo Park, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park, California, United States, (e-mail: ben@bolte.cc)","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"[Facebook AI Research Menlo Park, CA, USA]","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015826285","display_name":"Yao-Hung Hubert Tsai","orcid":"https://orcid.org/0000-0001-5312-1875"},"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":"Yao-Hung Hubert Tsai","raw_affiliation_strings":["Machine Learning Department, Carnegie Mellon University, 6612 Pittsburgh, Pennsylvania, United States, 15213-3815 (e-mail: yaohungt@cs.cmu.edu)","[Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Department, Carnegie Mellon University, 6612 Pittsburgh, Pennsylvania, United States, 15213-3815 (e-mail: yaohungt@cs.cmu.edu)","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA USA]","institution_ids":["https://openalex.org/I74973139"]}]},{"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"]},{"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, Menlo Park, California, United States, (e-mail: kushall@fb.com)","[Facebook AI Research Menlo Park, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park, California, United States, (e-mail: kushall@fb.com)","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"[Facebook AI Research Menlo Park, CA, USA]","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071983998","display_name":"Ruslan Salakhutdinov","orcid":"https://orcid.org/0000-0002-3752-2756"},"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":"Ruslan Salakhutdinov","raw_affiliation_strings":["Machine Learning Department, Carnegie Mellon University, 6612 Pittsburgh, Pennsylvania, United States, (e-mail: rsalakhu@cs.cmu.edu)","[Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Department, Carnegie Mellon University, 6612 Pittsburgh, Pennsylvania, United States, (e-mail: rsalakhu@cs.cmu.edu)","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA USA]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","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"]},{"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, Menlo Park, California, United States, 94025 (e-mail: abdo@fb.com)","[Facebook AI Research Menlo Park, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park, California, United States, 94025 (e-mail: abdo@fb.com)","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"[Facebook AI Research Menlo Park, CA, USA]","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":32.3668,"has_fulltext":true,"cited_by_count":269,"citation_normalized_percentile":{"value":0.99795088,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"3451","last_page":"3460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.7189045548439026},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6218289136886597},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5840944051742554},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5628824234008789},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5459372997283936},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4679509401321411},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.464537650346756},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.4627551734447479},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4447065591812134},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3498643636703491},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3358180522918701}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7189045548439026},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6218289136886597},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5840944051742554},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5628824234008789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5459372997283936},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4679509401321411},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.464537650346756},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.4627551734447479},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4447065591812134},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3498643636703491},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3358180522918701},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2021.3122291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3122291","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"},{"id":"pmh:oai:arXiv.org:2106.07447","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.07447","pdf_url":"https://arxiv.org/pdf/2106.07447","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3169320628","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.07447.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2106.07447","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.07447","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.07447","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.07447","pdf_url":"https://arxiv.org/pdf/2106.07447","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3169320628.pdf","grobid_xml":"https://content.openalex.org/works/W3169320628.grobid-xml"},"referenced_works_count":96,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1553004968","https://openalex.org/W2032210463","https://openalex.org/W2073459066","https://openalex.org/W2100768664","https://openalex.org/W2101234009","https://openalex.org/W2110073835","https://openalex.org/W2127141656","https://openalex.org/W2150593711","https://openalex.org/W2155273149","https://openalex.org/W2164579587","https://openalex.org/W2347098582","https://openalex.org/W2750248772","https://openalex.org/W2752796333","https://openalex.org/W2842511635","https://openalex.org/W2883725317","https://openalex.org/W2888911345","https://openalex.org/W2926827382","https://openalex.org/W2933138175","https://openalex.org/W2937090315","https://openalex.org/W2953190524","https://openalex.org/W2962739339","https://openalex.org/W2962850167","https://openalex.org/W2963341956","https://openalex.org/W2963618559","https://openalex.org/W2963799213","https://openalex.org/W2965373594","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2982223350","https://openalex.org/W2982399380","https://openalex.org/W2988736778","https://openalex.org/W2995181338","https://openalex.org/W2996383576","https://openalex.org/W2998532468","https://openalex.org/W3003875258","https://openalex.org/W3008525923","https://openalex.org/W3011411500","https://openalex.org/W3013571468","https://openalex.org/W3015265920","https://openalex.org/W3015522062","https://openalex.org/W3016011332","https://openalex.org/W3025035610","https://openalex.org/W3025165719","https://openalex.org/W3026041220","https://openalex.org/W3027083471","https://openalex.org/W3030163527","https://openalex.org/W3033038061","https://openalex.org/W3035060554","https://openalex.org/W3035202887","https://openalex.org/W3035524453","https://openalex.org/W3036224891","https://openalex.org/W3036601975","https://openalex.org/W3093533780","https://openalex.org/W3093579165","https://openalex.org/W3093788532","https://openalex.org/W3096338464","https://openalex.org/W3097777922","https://openalex.org/W3099782249","https://openalex.org/W3107668149","https://openalex.org/W3112034174","https://openalex.org/W3125709657","https://openalex.org/W3126816608","https://openalex.org/W3135676170","https://openalex.org/W3144810982","https://openalex.org/W3160799772","https://openalex.org/W3161101519","https://openalex.org/W4254197176","https://openalex.org/W6631190155","https://openalex.org/W6675022971","https://openalex.org/W6675354045","https://openalex.org/W6745117592","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6769196770","https://openalex.org/W6769311223","https://openalex.org/W6770514103","https://openalex.org/W6771917389","https://openalex.org/W6772883055","https://openalex.org/W6777232839","https://openalex.org/W6778883912","https://openalex.org/W6779326418","https://openalex.org/W6779997284","https://openalex.org/W6780218876","https://openalex.org/W6780483730","https://openalex.org/W6783797576","https://openalex.org/W6784436999","https://openalex.org/W6784614252","https://openalex.org/W6784637704","https://openalex.org/W6786614245","https://openalex.org/W6786669483","https://openalex.org/W6790168579","https://openalex.org/W6844194202","https://openalex.org/W6947929050"],"related_works":["https://openalex.org/W3209059054","https://openalex.org/W3099782249","https://openalex.org/W1494198834","https://openalex.org/W2842511635","https://openalex.org/W2972943112","https://openalex.org/W2963403868","https://openalex.org/W2963341956","https://openalex.org/W2936774411","https://openalex.org/W2995181338","https://openalex.org/W2982223350","https://openalex.org/W2973049979","https://openalex.org/W2127141656","https://openalex.org/W3157923770","https://openalex.org/W2996383576","https://openalex.org/W2933138175","https://openalex.org/W3098403858","https://openalex.org/W3016181583","https://openalex.org/W2726515241","https://openalex.org/W2146334809","https://openalex.org/W2964121744"],"abstract_inverted_index":{"Self-supervised":[0],"approaches":[1],"for":[2,59,75],"speech":[3,61],"representation":[4,62],"learning":[5],"are":[6,14],"challenged":[7],"by":[8],"three":[9,50],"unique":[10],"problems:":[11],"(1)":[12],"there":[13,23],"multiple":[15],"sound":[16,29,37],"units":[17,30,38],"in":[18],"each":[19],"input":[20,28],"utterance,":[21],"(2)":[22],"is":[24,86],"no":[25,43],"lexicon":[26],"of":[27,83,118,128,139,146],"during":[31],"the":[32,54,88,92,98,109,116,119,125,129,148,156,162,194],"pre-training":[33],"phase,":[34],"and":[35,105,142,165,174,188,198],"(3)":[36],"have":[39],"variable":[40],"lengths":[41],"with":[42,48,134,169],"explicit":[44],"segmentation.":[45],"To":[46],"deal":[47],"these":[49],"problems,":[51],"we":[52],"propose":[53],"Hidden-Unit":[55],"BERT":[56],"(HuBERT)":[57],"approach":[58,85],"self-supervised":[60],"learning,":[63],"which":[64,96],"utilizes":[65],"an":[66],"offline":[67],"clustering":[68,121],"step":[69,122],"to":[70,100,186],"provide":[71],"aligned":[72],"target":[73],"labels":[74],"a":[76,102,135,179],"BERT-like":[77],"prediction":[78,89],"loss.":[79],"A":[80],"key":[81],"ingredient":[82],"our":[84],"applying":[87],"loss":[90],"over":[91,108],"masked":[93],"regions":[94],"only,":[95],"forces":[97],"model":[99,107,150],"learn":[101],"combined":[103],"acoustic":[104],"language":[106],"continuous":[110],"inputs.":[111],"HuBERT":[112,149,183],"relies":[113],"primarily":[114],"on":[115,161,193],"consistency":[117],"unsupervised":[120],"rather":[123],"than":[124],"intrinsic":[126],"quality":[127],"assigned":[130],"cluster":[131],"labels.":[132],"Starting":[133],"simple":[136],"k-means":[137],"teacher":[138],"100":[140],"clusters,":[141],"using":[143],"two":[144],"iterations":[145],"clustering,":[147],"either":[151],"matches":[152],"or":[153],"improves":[154],"upon":[155],"state-of-the-art":[157],"wav2vec":[158],"2.0":[159],"performance":[160],"Librispeech":[163],"(960h)":[164],"Libri-light":[166],"(60,000h)":[167],"benchmarks":[168],"10min,":[170],"1h,":[171],"10h,":[172],"100h,":[173],"960h":[175],"fine-tuning":[176],"subsets.":[177,201],"Using":[178],"1B":[180],"parameter":[181],"model,":[182],"shows":[184],"up":[185],"19%":[187],"13%":[189],"relative":[190],"WER":[191],"reduction":[192],"more":[195],"challenging":[196],"dev-other":[197],"test-other":[199],"evaluation":[200]},"counts_by_year":[{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":93},{"year":2022,"cited_by_count":100},{"year":2021,"cited_by_count":25}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2022-07-25T00:00:00"}