{"id":"https://openalex.org/W4290995108","doi":"https://doi.org/10.1109/jstsp.2022.3198315","title":"C3-DINO: Joint Contrastive and Non-Contrastive Self-Supervised Learning for Speaker Verification","display_name":"C3-DINO: Joint Contrastive and Non-Contrastive Self-Supervised Learning for Speaker Verification","publication_year":2022,"publication_date":"2022-08-11","ids":{"openalex":"https://openalex.org/W4290995108","doi":"https://doi.org/10.1109/jstsp.2022.3198315"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3198315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3198315","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2208.07446","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005304261","display_name":"Chunlei Zhang","orcid":"https://orcid.org/0000-0002-3851-2357"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunlei Zhang","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3851-2357","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0520-6844","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210108985"],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":2.9463,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.91916551,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"16","issue":"6","first_page":"1273","last_page":"1283"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.996399998664856,"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":0.8060964941978455},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7059485912322998},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.679868221282959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5664305686950684},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5495570302009583},{"id":"https://openalex.org/keywords/contrastive-analysis","display_name":"Contrastive analysis","score":0.5444362163543701},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46454501152038574},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.430881530046463},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1772894561290741}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8060964941978455},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7059485912322998},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.679868221282959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5664305686950684},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5495570302009583},{"id":"https://openalex.org/C2777629044","wikidata":"https://www.wikidata.org/wiki/Q614959","display_name":"Contrastive analysis","level":2,"score":0.5444362163543701},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46454501152038574},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.430881530046463},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1772894561290741},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2022.3198315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3198315","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2208.07446","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.07446","pdf_url":"https://arxiv.org/pdf/2208.07446","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2208.07446","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.07446","pdf_url":"https://arxiv.org/pdf/2208.07446","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1936725236","https://openalex.org/W1985371235","https://openalex.org/W2159736522","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2290689761","https://openalex.org/W2696967604","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2787051072","https://openalex.org/W2794506738","https://openalex.org/W2802973008","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2936780106","https://openalex.org/W2962914040","https://openalex.org/W2963466847","https://openalex.org/W2963470929","https://openalex.org/W2969985801","https://openalex.org/W2972627751","https://openalex.org/W2972705840","https://openalex.org/W2973062255","https://openalex.org/W2982223350","https://openalex.org/W3000000254","https://openalex.org/W3013020904","https://openalex.org/W3015306128","https://openalex.org/W3024869864","https://openalex.org/W3035524453","https://openalex.org/W3097152652","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3161158930","https://openalex.org/W3161606033","https://openalex.org/W3202801947","https://openalex.org/W3206189675","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4200633018","https://openalex.org/W4224925084","https://openalex.org/W4286981691","https://openalex.org/W4297808394","https://openalex.org/W6631362777","https://openalex.org/W6688816777","https://openalex.org/W6752888775","https://openalex.org/W6755207826","https://openalex.org/W6772379172","https://openalex.org/W6774314701","https://openalex.org/W6776700526","https://openalex.org/W6777265123","https://openalex.org/W6779230768","https://openalex.org/W6779326418","https://openalex.org/W6780218876","https://openalex.org/W6781368565","https://openalex.org/W6784400926","https://openalex.org/W6801362334","https://openalex.org/W6844194202"],"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":{"Self-supervised":[0],"learning":[1,20,36,105],"(SSL)":[2],"has":[3],"drawn":[4],"an":[5,120],"increased":[6],"attention":[7],"in":[8,28,62,104,133],"the":[9,40,64,80,92,127,134,158,167,170,189,219,246,255,263,271,278,282,286],"field":[10],"of":[11,50,129,169,262,273],"speech":[12],"processing.":[13],"Recent":[14],"studies":[15,94],"have":[16],"demonstrated":[17],"that":[18,39,78,96,117],"contrastive":[19,34],"is":[21,69,144,250],"able":[22,251],"to":[23,119,157,177,187,252,257],"learn":[24],"discriminative":[25],"speaker":[26,83,106,163,190,195,232,248],"embeddings":[27,249],"a":[29,44,138,179,206,226,241],"self-supervised":[30,35],"manner.":[31],"However,":[32],"base":[33],"(CSSL)":[37],"assumes":[38],"pairs":[41,61,132],"generated":[42],"from":[43,87],"view":[45,49],"of$anchor$instance":[46],"and":[47,153,234,266,277,285],"any":[48],"other":[51],"instances":[52],"are":[53],"all":[54],"negative,":[55],"which":[56,72,155,217],"introduces":[57],"many":[58],"false":[59,130,147],"negative":[60,97,131,148,180],"constructing":[63],"loss":[65],"function.":[66],"The":[67,193],"problem":[68],"referred":[70],"as$class$-$collision$,":[71],"remains":[73],"as":[74],"one":[75],"major":[76],"issue":[77],"impedes":[79],"CSSL":[81,135,161,172],"based":[82,162],"verification":[84],"(SV)":[85],"systems":[86],"achieving":[88],"better":[89],"performances.":[90],"In":[91,110],"meanwhile,":[93],"reveal":[95],"sample":[98,181],"free":[99,182],"SSL":[100,115,183,222,283],"frameworks":[101],"perform":[102],"well":[103],"or":[107],"image":[108],"representations.":[109],"this":[111],"study,":[112],"we":[113,174],"investigate":[114],"techniques":[116],"lead":[118],"improved":[121],"SV":[122,284],"performance.":[123],"We":[124],"first":[125],"analyse":[126],"impact":[128],"systems.":[136],"Then,":[137],"multi-stage":[139],"Class-Collision":[140],"Correction":[141],"(C3)":[142],"method":[143,212],"proposed":[145,275],"(e.g.,":[146],"pair":[149],"filtering,":[150],"InfoNCE":[151],"re-weighting":[152],"ProtoNCE),":[154],"leads":[156],"state-of-the-art":[159],"(SOTA)":[160],"embedding":[164,191,196],"system.":[165],"On":[166],"basis":[168],"pretrained":[171],"model,":[173],"further":[175,253],"propose":[176],"employ":[178],"objective":[184],"(i.e.,":[185],"DINO)":[186],"fine-tune":[188],"network.":[192],"resulting":[194],"system":[197,223],"(C3-DINO)":[198],"achieves":[199],"2.5%":[200],"Equal":[201],"Error":[202],"Rate":[203],"(EER)":[204],"with":[205],"simple":[207],"Cosine":[208],"Distance":[209],"Scoring":[210],"(CDS)":[211],"on":[213,237,245],"Voxceleb1":[214],"test":[215],"set,":[216,240],"outperforms":[218],"previous":[220],"SOTA":[221],"(4.86%)":[224],"by":[225],"significant":[227],"+45%":[228],"relative":[229],"improvement.":[230],"With":[231],"clustering":[233],"pseudo":[235],"labeling":[236],"Voxceleb2":[238],"training":[239],"LDA/CDS":[242],"back-end":[243],"applying":[244],"C3-DINO":[247],"push":[254],"EER":[256],"2.2%.":[258],"Comprehensive":[259],"experimental":[260],"investigations":[261],"Voxceleb":[264],"benchmarks":[265],"our":[267,274],"internal":[268],"dataset":[269],"demonstrate":[270],"effectiveness":[272],"methods,":[276],"performance":[279],"gap":[280],"between":[281],"supervised":[287],"counterpart":[288],"narrows":[289],"further.":[290]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}