{"id":"https://openalex.org/W4392910494","doi":"https://doi.org/10.1109/icassp48485.2024.10448455","title":"Self-Supervised Speaker Verification with Adaptive Threshold and Hierarchical Training","display_name":"Self-Supervised Speaker Verification with Adaptive Threshold and Hierarchical Training","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910494","doi":"https://doi.org/10.1109/icassp48485.2024.10448455"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448455","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":"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/A5082214796","display_name":"Zehua Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"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":"Zehua Zhou","raw_affiliation_strings":["Tokyo Institute of Technology,Department of Information and Communications Engineering","Department of Information and Communications Engineering, Tokyo Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology,Department of Information and Communications Engineering","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Department of Information and Communications Engineering, Tokyo Institute of Technology","institution_ids":["https://openalex.org/I90023481","https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100573036","display_name":"Haoyuan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"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":"Haoyuan Yang","raw_affiliation_strings":["Tokyo Institute of Technology,Department of Information and Communications Engineering","Department of Information and Communications Engineering, Tokyo Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology,Department of Information and Communications Engineering","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Department of Information and Communications Engineering, Tokyo Institute of Technology","institution_ids":["https://openalex.org/I90023481","https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","orcid":"https://orcid.org/0000-0001-8114-8450"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"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":"Takahiro Shinozaki","raw_affiliation_strings":["Tokyo Institute of Technology,Department of Information and Communications Engineering","Department of Information and Communications Engineering, Tokyo Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology,Department of Information and Communications Engineering","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Department of Information and Communications Engineering, Tokyo Institute of Technology","institution_ids":["https://openalex.org/I90023481","https://openalex.org/I114531698"]}]}],"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":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12141","last_page":"12145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9939000010490417,"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":0.9939000010490417,"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":0.9631999731063843,"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":0.7923365831375122},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7908872961997986},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.608128011226654},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5285312533378601},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5176246762275696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4713945686817169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7923365831375122},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7908872961997986},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.608128011226654},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5285312533378601},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5176246762275696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4713945686817169},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448455","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"},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0006225263","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100911557","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5897303658","display_name":"Spoken Language Acquisition Agent with Fluent Intonation","funder_award_id":"22K12069","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W2150593711","https://openalex.org/W2219249508","https://openalex.org/W2222512263","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2883725317","https://openalex.org/W2890964092","https://openalex.org/W2921475306","https://openalex.org/W2969985801","https://openalex.org/W2979593053","https://openalex.org/W3013020904","https://openalex.org/W3015734344","https://openalex.org/W3023351797","https://openalex.org/W3024869864","https://openalex.org/W3159481202","https://openalex.org/W3160397447","https://openalex.org/W3161606033","https://openalex.org/W3163187953","https://openalex.org/W3205635414","https://openalex.org/W3211358952","https://openalex.org/W4221154746","https://openalex.org/W4286981691","https://openalex.org/W4296068770","https://openalex.org/W4297841416","https://openalex.org/W4310895557","https://openalex.org/W6688816777","https://openalex.org/W6697535213","https://openalex.org/W6762161020","https://openalex.org/W6779997284","https://openalex.org/W6784400926","https://openalex.org/W6796912519"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W3162054169","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"In":[0],"self-supervised":[1],"speaker":[2],"verification,":[3],"the":[4,14,23,40,44,59,82,98,106,122,126],"quality":[5],"of":[6,43,81,85,101,125],"generated":[7],"pseudo":[8],"labels":[9,28],"becomes":[10],"a":[11,19,33,69,109],"bottleneck":[12],"for":[13,71],"performance.":[15],"This":[16],"work":[17],"introduces":[18],"dynamic":[20],"threshold":[21],"within":[22],"iterative":[24],"DIstillation":[25],"with":[26,55,61,74,108],"NO":[27],"(DINO)":[29],"framework.":[30],"We":[31],"employ":[32],"Gaussian":[34],"Mixture":[35],"Model":[36],"(GMM)":[37],"to":[38,78,88,96,105],"model":[39],"loss":[41],"distribution":[42],"training":[45,95],"data.":[46],"The":[47],"GMM":[48],"has":[49],"two":[50,113],"components:":[51],"one":[52],"represents":[53],"samples":[54,73],"reliable":[56,75],"labels,":[57],"and":[58],"other":[60],"un-reliable":[62],"ones.":[63],"These":[64],"components":[65],"help":[66],"us":[67],"determine":[68],"thresh-old":[70],"retaining":[72],"labels.":[76,103],"Furthermore,":[77],"take":[79],"advantage":[80],"different":[83],"sensitivity":[84],"network":[86],"layers":[87],"label":[89],"noise,":[90],"we":[91],"further":[92],"introduce":[93],"hierarchical":[94],"reduce":[97],"negative":[99],"impact":[100],"unreliable":[102],"Compared":[104],"baseline":[107],"fixed":[110],"threshold,":[111],"our":[112],"strategies":[114],"result":[115],"in":[116],"an":[117],"8.9%":[118],"relative":[119],"improvement":[120],"on":[121],"Vox-O":[123],"trial":[124],"Voxceleb1":[127],"evaluation":[128],"dataset.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}