{"id":"https://openalex.org/W4372260593","doi":"https://doi.org/10.1109/icassp49357.2023.10094610","title":"Unsupervised Speaker Verification Using Pre-Trained Model and Label Correction","display_name":"Unsupervised Speaker Verification Using Pre-Trained Model and Label Correction","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260593","doi":"https://doi.org/10.1109/icassp49357.2023.10094610"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5023757704","display_name":"Zhicong Chen","orcid":"https://orcid.org/0000-0002-3471-6395"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicong Chen","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,China","School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440047","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0002-1262-6719"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,China","School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034717070","display_name":"Wenxuan Hu","orcid":"https://orcid.org/0000-0003-1222-459X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxuan Hu","raw_affiliation_strings":["Xiamen University,School of Informatics,China","School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412926","display_name":"Lin Li","orcid":"https://orcid.org/0000-0003-0426-6546"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,China","School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":["Xiamen University,School of Informatics,China","School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.991100013256073,"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":0.9901999831199646,"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":0.8474050760269165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5987143516540527},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5981494188308716},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5615144371986389},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5438592433929443},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4685942232608795},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4574744701385498},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43837589025497437},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.42745786905288696},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.4220839738845825},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.40721645951271057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8474050760269165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5987143516540527},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5981494188308716},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5615144371986389},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5438592433929443},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4685942232608795},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4574744701385498},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43837589025497437},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.42745786905288696},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4220839738845825},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.40721645951271057},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/16","display_name":"Peace, Justice and strong institutions","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2164998314","https://openalex.org/W2187089797","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2964054038","https://openalex.org/W3024869864","https://openalex.org/W3036601975","https://openalex.org/W3163187953","https://openalex.org/W3163421828","https://openalex.org/W3196649213","https://openalex.org/W3197580070","https://openalex.org/W3198275944","https://openalex.org/W3198429080","https://openalex.org/W3202370288","https://openalex.org/W3205635414","https://openalex.org/W3206189675","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221161148","https://openalex.org/W4224934182","https://openalex.org/W4226254439","https://openalex.org/W4286981691","https://openalex.org/W4296068420","https://openalex.org/W4296068770","https://openalex.org/W4385245566","https://openalex.org/W6780218876","https://openalex.org/W6784400926","https://openalex.org/W6800698692","https://openalex.org/W6810126160"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W3141593045","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"Recently,":[0],"the":[1,28,47,58,62,97,114],"fine-tuning":[2],"pre-trained":[3],"model":[4,76],"framework":[5],"has":[6],"emerged":[7],"as":[8],"a":[9,20,37,73,78,81],"promising":[10],"paradigm":[11],"for":[12,23],"speech-processing":[13],"tasks.":[14],"In":[15],"this":[16],"study,":[17],"we":[18,51],"present":[19],"novel":[21],"strategy":[22],"unsupervised":[24],"speaker":[25,74],"verification":[26,75],"using":[27],"Sub-structure":[29],"of":[30,36,99],"Pre-Trained":[31],"Model":[32],"(Sub-PTM),":[33],"which":[34],"consists":[35],"CNN-based":[38],"feature":[39],"extractor":[40],"and":[41,80,89],"several":[42],"Transformer":[43],"blocks.":[44],"To":[45],"obtain":[46],"initial":[48],"pseudo":[49,66,101],"labels,":[50],"utilize":[52],"Infomap":[53],"to":[54,71,95,113],"perform":[55],"clustering":[56],"on":[57],"representations":[59],"extracted":[60],"from":[61],"Sub-PTM.":[63],"The":[64],"generated":[65],"labels":[67],"are":[68],"then":[69],"leveraged":[70],"train":[72],"containing":[77],"Sub-PTM":[79],"downstream":[82],"network.":[83],"We":[84],"also":[85],"propose":[86],"an":[87],"Online":[88],"Offline":[90],"Label":[91],"Correction":[92],"(OAO-LC)":[93],"method":[94],"alleviate":[96],"effects":[98],"incorrect":[100],"labels.":[102],"By":[103],"incorporating":[104],"these":[105],"techniques,":[106],"our":[107],"system":[108],"achieves":[109],"competitive":[110],"results":[111],"compared":[112],"supervised":[115],"baseline.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
