{"id":"https://openalex.org/W4224927737","doi":"https://doi.org/10.1109/icassp43922.2022.9746097","title":"An Exploration of Hubert with Large Number of Cluster Units and Model Assessment Using Bayesian Information Criterion","display_name":"An Exploration of Hubert with Large Number of Cluster Units and Model Assessment Using Bayesian Information Criterion","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224927737","doi":"https://doi.org/10.1109/icassp43922.2022.9746097"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746097","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5059612504","display_name":"Takashi Maekaku","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi Maekaku","raw_affiliation_strings":["Yahoo Japan Corporation,Tokyo,Japan","Yahoo Japan Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, Japan","institution_ids":[]}]},{"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,PA,USA","Carnegie Mellon University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040732498","display_name":"Yuya Fujita","orcid":"https://orcid.org/0000-0001-8155-6040"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuya Fujita","raw_affiliation_strings":["Yahoo Japan Corporation,Tokyo,Japan","Yahoo Japan Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","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,PA,USA","Carnegie Mellon University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7107","last_page":"7111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987999796867371,"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/T12031","display_name":"Speech and dialogue systems","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8275841474533081},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6258729696273804},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6174031496047974},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5151435136795044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49724963307380676},{"id":"https://openalex.org/keywords/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.46865954995155334},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.45522817969322205},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4342251121997833},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4308593273162842},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36579468846321106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8275841474533081},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6258729696273804},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6174031496047974},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5151435136795044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49724963307380676},{"id":"https://openalex.org/C168136583","wikidata":"https://www.wikidata.org/wiki/Q1988242","display_name":"Bayesian information criterion","level":2,"score":0.46865954995155334},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.45522817969322205},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4342251121997833},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4308593273162842},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36579468846321106},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746097","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1963627370","https://openalex.org/W2123799894","https://openalex.org/W2152790380","https://openalex.org/W2168175751","https://openalex.org/W2395899413","https://openalex.org/W2405331948","https://openalex.org/W2741692265","https://openalex.org/W2896457183","https://openalex.org/W2965373594","https://openalex.org/W2975381464","https://openalex.org/W2982223350","https://openalex.org/W2995181338","https://openalex.org/W2996728628","https://openalex.org/W3016011332","https://openalex.org/W3036601975","https://openalex.org/W3093096176","https://openalex.org/W3160799772","https://openalex.org/W3163793923","https://openalex.org/W3197259906","https://openalex.org/W3197349023","https://openalex.org/W3197381195","https://openalex.org/W3197580070","https://openalex.org/W3198815374","https://openalex.org/W3207558756","https://openalex.org/W4287173589","https://openalex.org/W4287591426","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W4394671563","https://openalex.org/W6641076745","https://openalex.org/W6682948231","https://openalex.org/W6739901393","https://openalex.org/W6766673545","https://openalex.org/W6768080748","https://openalex.org/W6770941677","https://openalex.org/W6780218876","https://openalex.org/W6784531339","https://openalex.org/W6786696081","https://openalex.org/W6790356757","https://openalex.org/W6794548583","https://openalex.org/W6795346631","https://openalex.org/W6795952400","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2081647779","https://openalex.org/W3185852197","https://openalex.org/W3107474891","https://openalex.org/W4205820553","https://openalex.org/W2995335655","https://openalex.org/W142374489","https://openalex.org/W2359001871","https://openalex.org/W1803932089","https://openalex.org/W2374918184","https://openalex.org/W1985007624"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"has":[3,53],"become":[4],"one":[5,33],"of":[6,34,80,103,119,171],"the":[7,35,94,100,104,113,123,127,136,168,192],"most":[8],"important":[9],"technologies":[10],"to":[11,37,86,173],"realize":[12],"spoken":[13],"dialogue":[14],"systems":[15],"for":[16,126,166,191],"languages":[17],"that":[18,109,159,185],"do":[19],"not":[20],"have":[21,41,66],"much":[22],"audio":[23],"data":[24],"and":[25,40,71,82,179],"its":[26],"transcription":[27],"available.":[28],"Speech":[29,130],"representation":[30],"models":[31],"are":[32,188],"keys":[36],"achieving":[38],"this,":[39],"been":[42],"actively":[43],"studied":[44],"in":[45,57,84,116,122],"recent":[46],"years.":[47],"Among":[48],"them,":[49],"Hidden-Unit":[50],"BERT":[51],"(HuBERT)":[52],"shown":[54],"promising":[55],"results":[56,107],"automatic":[58],"speech":[59,89],"recognition":[60],"(ASR)":[61],"tasks.":[62],"However,":[63],"previous":[64],"studies":[65],"investigated":[67],"with":[68,77,141,152],"limited":[69],"iterations":[70,83],"cluster":[72],"units.":[73],"We":[74],"explore":[75],"HuBERT":[76,137],"larger":[78],"numbers":[79],"clusters":[81,172],"order":[85],"obtain":[87],"better":[88],"representation.":[90],"Furthermore,":[91],"we":[92,157,183],"introduce":[93],"Bayesian":[95],"Information":[96],"Criterion":[97],"(BIC)":[98],"as":[99,163],"performance":[101,115,175],"measure":[102],"model.":[105],"Experimental":[106],"show":[108,184],"our":[110,147],"model":[111,139,148],"achieves":[112],"best":[114],"5":[117],"out":[118],"8":[120],"scores":[121],"4":[124],"metrics":[125],"Zero":[128],"Resource":[129],"2021":[131],"task.":[132,194],"It":[133],"also":[134,189],"outperforms":[135],"BASE":[138],"trained":[140,151],"960-hour":[142],"LibriSpeech":[143],"(LS)":[144],"even":[145],"though":[146],"is":[149,161],"only":[150],"100-hour":[153],"LS.":[154],"In":[155],"addition,":[156],"report":[158],"BIC":[160],"useful":[162],"a":[164],"clue":[165],"determining":[167],"appropriate":[169],"number":[170],"improve":[174],"on":[176],"phonetic,":[177],"lexical,":[178],"syntactic":[180],"metrics.":[181],"Finally,":[182],"these":[186],"findings":[187],"effective":[190],"ASR":[193]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}