{"id":"https://openalex.org/W4416250289","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228223","title":"Enhancing Self-Supervised Speaker Verification Using Similarity-Connected Graphs and GCN","display_name":"Enhancing Self-Supervised Speaker Verification Using Similarity-Connected Graphs and GCN","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250289","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228223"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":null,"display_name":"Zhaorui Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaorui Sun","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101732742","display_name":"Yi\u2010Hao Chen","orcid":"https://orcid.org/0000-0002-9977-7180"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihao Chen","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045230762","display_name":"Jialong Wang","orcid":"https://orcid.org/0009-0008-7961-8511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jialong Wang","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413867","display_name":"Minqiang Xu","orcid":"https://orcid.org/0000-0003-3625-1736"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minqiang Xu","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074900997","display_name":"Jianbo Zhan","orcid":"https://orcid.org/0000-0002-5885-1970"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianbo Zhan","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044739051","display_name":"Lei Fang","orcid":"https://orcid.org/0000-0002-1438-2500"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Fang","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sian Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sian Fang","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037906509","display_name":"Lin Liu","orcid":"https://orcid.org/0000-0003-4173-7650"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Liu","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32178746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.854200005531311,"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":0.854200005531311,"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":0.020600000396370888,"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/T10057","display_name":"Face and Expression Recognition","score":0.013399999588727951,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/cluster-analysis","display_name":"Cluster analysis","score":0.7103999853134155},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6381999850273132},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45570001006126404},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4422999918460846},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.39660000801086426},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.38190001249313354},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.364300012588501},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.35569998621940613},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.35510000586509705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8090000152587891},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7103999853134155},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6381999850273132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.573199987411499},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4650000035762787},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45570001006126404},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45410001277923584},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.35569998621940613},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3546000123023987},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.2685000002384186},{"id":"https://openalex.org/C39235581","wikidata":"https://www.wikidata.org/wiki/Q5158434","display_name":"Conceptual clustering","level":5,"score":0.26649999618530273},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2002016471","https://openalex.org/W2122111042","https://openalex.org/W2154278880","https://openalex.org/W2604314403","https://openalex.org/W2696967604","https://openalex.org/W2808631503","https://openalex.org/W2921475306","https://openalex.org/W2945827377","https://openalex.org/W2963854930","https://openalex.org/W2972705840","https://openalex.org/W3013020904","https://openalex.org/W3015734344","https://openalex.org/W3023351797","https://openalex.org/W3024869864","https://openalex.org/W3159481202","https://openalex.org/W3163187953","https://openalex.org/W3205635414","https://openalex.org/W3211358952","https://openalex.org/W4200633018","https://openalex.org/W4296068770","https://openalex.org/W4372346385","https://openalex.org/W4402111362"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,28,39,46,59,67,103,113,118,125,158,164,168,174,181,186],"continuous":[2],"development":[3],"of":[4,30,41,49,117,124,176,185],"speech":[5,92],"recognition":[6,115],"technology,":[7],"speaker":[8,188,209],"verification":[9,189],"(SV)":[10],"has":[11,33,72],"become":[12,73],"an":[13,82,134],"important":[14],"method":[15,86,196],"for":[16,99,207],"identity":[17],"authentication.":[18],"Traditional":[19],"SV":[20],"methods":[21,52],"rely":[22],"on":[23,139],"handcrafted":[24],"feature":[25],"extraction,":[26],"while":[27],"introduction":[29],"deep":[31,50],"learning":[32,51,85],"significantly":[34,198],"improved":[35,135],"system":[36,119,200],"performance.":[37],"However,":[38,102],"scarcity":[40],"labeled":[42],"data":[43,93,155],"still":[44],"limits":[45],"widespread":[47],"application":[48],"in":[53,62,152,163],"SV.":[54],"Self-supervised":[55],"learning,":[56],"by":[57],"mining":[58],"latent":[60],"information":[61,160],"massive":[63],"unlabeled":[64,91],"data,":[65],"enhances":[66],"model\u2019s":[68,126],"generalization":[69],"ability":[70],"and":[71,120,143,156,178,183,202],"a":[74,204],"key":[75],"technology":[76],"to":[77],"address":[78,128],"this":[79,129,131,195],"issue.DINO":[80],"is":[81,171],"efficient":[83],"self-supervised":[84,187,208],"that":[87,194],"generates":[88],"pseudo-labels":[89,177],"from":[90],"through":[94],"clustering":[95,104,136,169],"algorithms,":[96],"providing":[97],"support":[98],"subsequent":[100],"training.":[101],"process":[105,170],"may":[106],"produce":[107],"noisy":[108],"pseudolabels,":[109],"which":[110],"can":[111,197],"reduce":[112],"overall":[114],"performance":[116,184,201],"restrict":[121],"further":[122],"improvement":[123],"performance.To":[127],"issue,":[130],"paper":[132],"proposes":[133],"framework":[137],"based":[138],"similarity":[140,165],"connection":[141,166],"graphs":[142],"Graph":[144],"Convolutional":[145],"Networks":[146],"(GCN).":[147],"By":[148],"leveraging":[149],"GCN\u2019s":[150],"strength":[151],"modeling":[153],"structured":[154],"incorporating":[157],"relational":[159],"between":[161],"nodes":[162],"graph,":[167],"optimized,":[172],"improving":[173],"accuracy":[175],"thereby":[179],"enhancing":[180],"robustness":[182],"system.":[190],"Experimental":[191],"results":[192],"show":[193],"improve":[199],"provide":[203],"new":[205],"approach":[206],"verification.":[210]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-14T00:00:00"}