{"id":"https://openalex.org/W4392903509","doi":"https://doi.org/10.1109/icassp48485.2024.10448052","title":"Hubertopic: Enhancing Semantic Representation of Hubert Through Self-Supervision Utilizing Topic Model","display_name":"Hubertopic: Enhancing Semantic Representation of Hubert Through Self-Supervision Utilizing Topic Model","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903509","doi":"https://doi.org/10.1109/icassp48485.2024.10448052"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448052","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448052","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":"https://openalex.org/A5059612504","display_name":"Takashi Maekaku","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takashi Maekaku","raw_affiliation_strings":["LY Corporation,Tokyo,Japan","LY Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"LY Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"LY Corporation, Tokyo, Japan","institution_ids":[]}]},{"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/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":"Jiatong Shi","raw_affiliation_strings":["Carnegie Mellon University,PA,USA","Carnegie Mellon University, PA, USA"],"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/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"],"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":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuya Fujita","raw_affiliation_strings":["LY Corporation,Tokyo,Japan","LY Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"LY Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"LY 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"],"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":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059612504"],"corresponding_institution_ids":["https://openalex.org/I4210096607"],"apc_list":null,"apc_paid":null,"fwci":0.3345,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61136841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"33","issue":null,"first_page":"11741","last_page":"11745"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"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/T12031","display_name":"Speech and dialogue systems","score":0.9970999956130981,"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":0.8588383197784424},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7852703332901001},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.645907461643219},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6379674673080444},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6358062624931335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6342113018035889},{"id":"https://openalex.org/keywords/theme","display_name":"Theme (computing)","score":0.47454890608787537},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32649725675582886},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09475201368331909}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8588383197784424},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7852703332901001},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.645907461643219},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6379674673080444},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6358062624931335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6342113018035889},{"id":"https://openalex.org/C33566652","wikidata":"https://www.wikidata.org/wiki/Q1065927","display_name":"Theme (computing)","level":2,"score":0.47454890608787537},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32649725675582886},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09475201368331909},{"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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448052","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448052","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.550000011920929}],"awards":[{"id":"https://openalex.org/G1912064254","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4006316252","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G509285653","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7622549653","display_name":null,"funder_award_id":"213829","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8300691027","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W108866686","https://openalex.org/W1494198834","https://openalex.org/W2896457183","https://openalex.org/W2962780374","https://openalex.org/W3036601975","https://openalex.org/W3140429000","https://openalex.org/W3160799772","https://openalex.org/W3189296823","https://openalex.org/W3197580070","https://openalex.org/W3207558756","https://openalex.org/W3209984917","https://openalex.org/W4220861476","https://openalex.org/W4221142221","https://openalex.org/W4226033575","https://openalex.org/W4231510805","https://openalex.org/W4281492411","https://openalex.org/W4285250921","https://openalex.org/W4296068815","https://openalex.org/W4319862410","https://openalex.org/W4372260526","https://openalex.org/W4372347505","https://openalex.org/W4375869237","https://openalex.org/W4382202628","https://openalex.org/W4385822439","https://openalex.org/W4385822740","https://openalex.org/W4385823059","https://openalex.org/W6639619044","https://openalex.org/W6780218876","https://openalex.org/W6810311456","https://openalex.org/W6810673746","https://openalex.org/W6839738141"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2314871050"],"abstract_inverted_index":{"Recently,":[0],"the":[1,33,45,51,55,94,153,166,190],"usefulness":[2],"of":[3,17,58,71,79,97,165,192],"self-supervised":[4],"representation":[5,36,96],"learning":[6,56],"(SSRL)":[7],"methods":[8],"has":[9],"been":[10],"confirmed":[11],"in":[12,137,155,195],"various":[13,177],"downstream":[14],"tasks.":[15,169],"Many":[16],"these":[18],"models,":[19],"as":[20,76,126,182],"exemplified":[21],"by":[22,122],"HuBERT":[23,121],"and":[24,65,81,162,185],"WavLM,":[25],"use":[26,70],"pseudo-labels":[27,46,104],"generated":[28],"from":[29],"spectral":[30],"features":[31],"or":[32,149],"model\u2019s":[34],"own":[35],"features.":[37],"From":[38],"previous":[39],"studies,":[40],"it":[41],"is":[42,118],"known":[43],"that":[44,144,173],"contain":[47],"semantic":[48,73,95,132,198],"information.":[49],"However,":[50],"masked":[52],"prediction":[53],"task,":[54],"criterion":[57],"HuBERT,":[59],"focuses":[60],"on":[61],"local":[62],"contextual":[63],"information":[64,74,133,178],"may":[66],"not":[67],"make":[68],"effective":[69],"global":[72,131],"such":[75,181],"speaker,":[77,184],"theme":[78],"speech,":[80],"so":[82],"on.":[83],"In":[84],"this":[85],"paper,":[86],"we":[87,171],"propose":[88],"a":[89,107],"new":[90],"approach":[91,194],"to":[92,103,105,120,134],"enrich":[93],"HuBERT.":[98],"We":[99],"apply":[100],"topic":[101,108,115,124,174],"model":[102],"generate":[106],"label":[109],"for":[110],"each":[111],"utterance.":[112],"An":[113],"auxiliary":[114],"classification":[116],"task":[117],"added":[119],"using":[123],"labels":[125,175],"teachers.":[127],"This":[128,188],"allows":[129],"additional":[130],"be":[135],"incorporated":[136],"an":[138],"unsupervised":[139],"manner.":[140],"Experimental":[141],"results":[142],"demonstrate":[143],"our":[145,193],"method":[146],"achieves":[147],"comparable":[148],"better":[150],"performance":[151],"than":[152],"baseline":[154],"most":[156],"tasks,":[157],"including":[158],"automatic":[159],"speech":[160],"recognition":[161],"five":[163],"out":[164],"eight":[167],"SUPERB":[168],"Moreover,":[170],"find":[172],"include":[176],"about":[179],"utterance,":[180],"gender,":[183],"its":[186],"theme.":[187],"highlights":[189],"effectiveness":[191],"capturing":[196],"multifaceted":[197],"nuances.":[199]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}