{"id":"https://openalex.org/W4400579178","doi":"https://doi.org/10.1109/taslp.2024.3426934","title":"Unsupervised Adaptive Speaker Recognition by Coupling-Regularized Optimal Transport","display_name":"Unsupervised Adaptive Speaker Recognition by Coupling-Regularized Optimal Transport","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400579178","doi":"https://doi.org/10.1109/taslp.2024.3426934"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3426934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426934","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/A5015972984","display_name":"Ruiteng Zhang","orcid":"https://orcid.org/0000-0002-9113-2206"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruiteng Zhang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027428789","display_name":"Jianguo Wei","orcid":"https://orcid.org/0000-0002-8964-9759"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianguo Wei","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082286929","display_name":"Wenhuan Lu","orcid":"https://orcid.org/0000-0002-7951-8907"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhuan Lu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012455357","display_name":"Di Jin","orcid":"https://orcid.org/0000-0002-7445-9936"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Jin","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351795","display_name":"Lin Zhang","orcid":"https://orcid.org/0000-0001-7826-2850"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lin Zhang","raw_affiliation_strings":["Brno University of Technology, Brno, Czechia"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Brno, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006839468","display_name":"Junhai Xu","orcid":"https://orcid.org/0000-0002-4289-647X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhai Xu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5015972984"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":1.3901,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8390815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"3603","last_page":"3617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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":0.9925000071525574,"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/coupling","display_name":"Coupling (piping)","score":0.5903221368789673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5064092874526978},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4842967092990875},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3909977972507477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36275845766067505},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10341951251029968}],"concepts":[{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.5903221368789673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5064092874526978},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4842967092990875},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3909977972507477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36275845766067505},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10341951251029968},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3426934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426934","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":[],"awards":[{"id":"https://openalex.org/G6571002837","display_name":null,"funder_award_id":"92370111","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8216993767","display_name":null,"funder_award_id":"62176181","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1594039573","https://openalex.org/W2040266692","https://openalex.org/W2046015436","https://openalex.org/W2070176749","https://openalex.org/W2075138946","https://openalex.org/W2095705004","https://openalex.org/W2099111195","https://openalex.org/W2107328749","https://openalex.org/W2121812409","https://openalex.org/W2125865219","https://openalex.org/W2129244720","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2360384684","https://openalex.org/W2531958295","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2801581493","https://openalex.org/W2889048668","https://openalex.org/W2901368553","https://openalex.org/W2928165649","https://openalex.org/W2936780106","https://openalex.org/W2963187488","https://openalex.org/W2963242190","https://openalex.org/W2963446838","https://openalex.org/W2963466847","https://openalex.org/W2969985801","https://openalex.org/W2972743990","https://openalex.org/W2972986505","https://openalex.org/W3015546017","https://openalex.org/W3015915933","https://openalex.org/W3024869864","https://openalex.org/W3034337242","https://openalex.org/W3034756453","https://openalex.org/W3084783920","https://openalex.org/W3097244734","https://openalex.org/W3116256056","https://openalex.org/W3160646455","https://openalex.org/W3162130072","https://openalex.org/W3163150275","https://openalex.org/W3167533889","https://openalex.org/W3171007011","https://openalex.org/W3208777959","https://openalex.org/W3217778739","https://openalex.org/W4220961503","https://openalex.org/W4221154746","https://openalex.org/W4226329757","https://openalex.org/W4292387508","https://openalex.org/W4307357910","https://openalex.org/W4312636357","https://openalex.org/W4321608821","https://openalex.org/W4372349064","https://openalex.org/W4376456958","https://openalex.org/W4382051493","https://openalex.org/W4385823137","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6639480849","https://openalex.org/W6674330103","https://openalex.org/W6675038308","https://openalex.org/W6679390333","https://openalex.org/W6682962330","https://openalex.org/W6688816777","https://openalex.org/W6737976933","https://openalex.org/W6754473786","https://openalex.org/W6769178842","https://openalex.org/W6792033799","https://openalex.org/W6803559545","https://openalex.org/W6810752947"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Cross-domain":[0],"speaker":[1,27,44,206],"recognition":[2],"(SR)":[3],"can":[4],"be":[5],"improved":[6],"by":[7],"unsupervised":[8],"domain":[9,17,39],"adaptation":[10],"(UDA)":[11],"algorithms.":[12],"UDA":[13,48],"algorithms":[14],"often":[15],"reduce":[16,83,106],"mismatch":[18],"at":[19],"the":[20,24,35,43,61,84,90,107,113,121,125,165,173,177,182,191,194,232],"cost":[21],"of":[22,26,176,184,193],"decreasing":[23],"discrimination":[25,45],"features.":[28,211],"In":[29,112],"contrast,":[30],"optimal":[31,98],"transport":[32,99,109,186],"(OT)":[33],"has":[34],"potential":[36],"to":[37,54,73,105,154,158,171,227],"achieve":[38],"alignment":[40],"while":[41],"preserving":[42],"capability":[46],"in":[47,78,187,222],"applications;":[49],"however,":[50],"naively":[51],"applying":[52],"OT":[53,126],"measure":[55],"global":[56],"probability":[57],"distribution":[58],"discrepancies":[59],"between":[60],"source":[62],"and":[63,134,209],"target":[64,204],"domains":[65],"may":[66],"induce":[67],"negative":[68,81,108,185],"transports":[69,82],"where":[70],"samples":[71,157,162],"belonging":[72],"different":[74,203],"speakers":[75],"are":[76,163],"coupled":[77],"transportation.":[79],"These":[80],"SR":[85,91,104,198],"model's":[86],"discriminative":[87],"power,":[88],"degrading":[89],"performance.":[92],"This":[93],"paper":[94],"proposes":[95],"a":[96,128,135,144,218],"coupling-regularized":[97],"(CROT)":[100],"algorithm":[101],"for":[102,124],"cross-domain":[103,197],"during":[110],"UDA.":[111,188],"proposed":[114,195],"CROT,":[115],"two":[116],"consecutive":[117],"processing":[118],"modules":[119],"regularize":[120],"coupling":[122,161,178],"paths":[123,179],"solution:":[127],"progressive":[129],"inter-speaker":[130],"constraint":[131],"(PISC)":[132],"module":[133],"coupling-smoothed":[136],"regularization":[137],"(CSR)":[138],"module.":[139],"The":[140,168],"PISC,":[141],"designed":[142,170],"as":[143],"pseudo-label":[145],"memory":[146],"bank":[147],"with":[148],"curriculum":[149],"learning,":[150],"is":[151],"first":[152],"applied":[153],"select":[155],"valid":[156],"guarantee":[159],"that":[160,215],"from":[164],"same":[166],"speaker.":[167],"CSR,":[169],"control":[172],"information":[174],"entropy":[175],"further,":[180],"reduces":[181],"effect":[183],"To":[189],"evaluate":[190],"effectiveness":[192],"algorithm,":[196],"experiments":[199],"were":[200],"conducted":[201],"under":[202],"domains,":[205],"encoders,":[207],"corpora,":[208],"acoustic":[210],"Experimental":[212],"results":[213],"showed":[214],"CROT":[216],"achieved":[217],"50%":[219],"relative":[220],"reduction":[221],"equal":[223],"error":[224],"rates":[225],"compared":[226],"conventional":[228],"OT-based":[229],"UDAs,":[230],"outperforming":[231],"state-of-the-art":[233],"UDAs.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}