{"id":"https://openalex.org/W4225287119","doi":"https://doi.org/10.1109/icassp43922.2022.9747209","title":"Robust Speaker Verification with Joint Self-Supervised and Supervised Learning","display_name":"Robust Speaker Verification with Joint Self-Supervised and Supervised Learning","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225287119","doi":"https://doi.org/10.1109/icassp43922.2022.9747209"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747209","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":"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/A5100436995","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0002-1617-5804"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Wang","raw_affiliation_strings":["Samsung R&D Institute China Xian"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China Xian","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolei Zhang","raw_affiliation_strings":["Samsung R&D Institute China Xian"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China Xian","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376483","display_name":"Miao Zhang","orcid":"https://orcid.org/0000-0002-8952-215X"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao Zhang","raw_affiliation_strings":["Samsung R&D Institute China Xian"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China Xian","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039487617","display_name":"Yuguang Li","orcid":"https://orcid.org/0000-0002-8927-3536"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuguang Li","raw_affiliation_strings":["Samsung R&D Institute China Xian"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute China Xian","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101750948","display_name":"Jaeyun Lee","orcid":"https://orcid.org/0000-0002-4631-6380"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeyun Lee","raw_affiliation_strings":["Samsung Advanced Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101408880","display_name":"Kiho Cho","orcid":"https://orcid.org/0000-0001-6067-9447"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kiho Cho","raw_affiliation_strings":["Samsung Advanced Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043574348","display_name":"Sung-UN Park","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung-UN Park","raw_affiliation_strings":["Samsung Advanced Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100436995"],"corresponding_institution_ids":["https://openalex.org/I4210155230"],"apc_list":null,"apc_paid":null,"fwci":0.2078,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.37432665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7637","last_page":"7641"},"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":0.9987999796867371,"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":0.9980999827384949,"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":0.8368175625801086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6830374002456665},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6444639563560486},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.6034560799598694},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5734773278236389},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5690698027610779},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5467764139175415},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5389744639396667},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5004043579101562},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.49094656109809875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4485696852207184},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4135206341743469},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41260826587677},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3823842406272888},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3767619729042053},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14492997527122498}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8368175625801086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6830374002456665},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6444639563560486},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.6034560799598694},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5734773278236389},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5690698027610779},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5467764139175415},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5389744639396667},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5004043579101562},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.49094656109809875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4485696852207184},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4135206341743469},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41260826587677},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3823842406272888},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3767619729042053},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14492997527122498},{"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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747209","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2187089797","https://openalex.org/W2191779130","https://openalex.org/W2603777577","https://openalex.org/W2726515241","https://openalex.org/W2747238065","https://openalex.org/W2788991015","https://openalex.org/W2794506738","https://openalex.org/W2802973008","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2952218014","https://openalex.org/W2963242190","https://openalex.org/W2963420686","https://openalex.org/W2972659941","https://openalex.org/W2972705840","https://openalex.org/W2972986505","https://openalex.org/W2983398075","https://openalex.org/W3013020904","https://openalex.org/W3099330747","https://openalex.org/W3100517161","https://openalex.org/W3119029376","https://openalex.org/W3150964372","https://openalex.org/W3160397447","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W4312414840","https://openalex.org/W2794908468","https://openalex.org/W4206276646","https://openalex.org/W2943467239","https://openalex.org/W1571801203","https://openalex.org/W101422005","https://openalex.org/W192740413","https://openalex.org/W3004135598","https://openalex.org/W2952937263","https://openalex.org/W2131153761"],"abstract_inverted_index":{"Supervised":[0,8],"learning":[1,4,9,69],"and":[2,50,111,119,122,125],"self-supervised":[3,22,67,79],"address":[5],"different":[6],"facets.":[7],"achieves":[10],"high":[11,53],"accuracy,":[12],"but":[13,32],"it":[14],"requires":[15],"numerous":[16],"expensive":[17],"labeled":[18],"data":[19,29,49],"indeed.":[20],"Correspondingly,":[21],"learning,":[23],"makes":[24],"use":[25],"of":[26,38,46,58,133],"abundant":[27],"unlabeled":[28],"to":[30,93,102],"learn,":[31],"the":[33,39,44,52,56,74,89,140],"performance":[34,54],"lags":[35],"behind":[36],"that":[37,98],"supervised":[40,75],"counterpart.":[41],"To":[42],"overcome":[43],"difficulty":[45],"acquiring":[47],"annotated":[48],"contain":[51],"in":[55,63,82,131],"context":[57],"speaker":[59,90,96],"verification,":[60],"we":[61],"propose":[62],"this":[64],"work":[65],"a":[66],"joint":[68,83],"(SS-JL)":[70],"framework":[71],"which":[72],"complements":[73],"main":[76],"task":[77],"with":[78,139],"auxiliary":[80,86],"tasks":[81,87],"training.":[84],"These":[85],"help":[88],"verification":[91],"pipeline":[92],"generate":[94],"robust":[95],"representation":[97],"is":[99,106,128],"closely":[100],"relevant":[101],"voiceprints.":[103],"Our":[104],"model":[105],"trained":[107],"on":[108,113],"English":[109],"dataset":[110],"tested":[112],"multilingual":[114],"datasets,":[115,121],"including":[116],"English,":[117],"Chinese":[118],"Korean":[120],"13.6%,":[123],"12.7%":[124],"13.5%":[126],"improvement":[127],"achieved":[129],"respectively":[130],"terms":[132],"equal":[134],"error":[135],"rate":[136],"(EER)":[137],"compared":[138],"baselines.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}