{"id":"https://openalex.org/W4296068770","doi":"https://doi.org/10.21437/interspeech.2022-742","title":"Self-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correction","display_name":"Self-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correction","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068770","doi":"https://doi.org/10.21437/interspeech.2022-742"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-742","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-742","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5100767961","display_name":"Bing Han","orcid":"https://orcid.org/0009-0009-1821-6161"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Han","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101416769","display_name":"Zhengyang Chen","orcid":"https://orcid.org/0000-0003-1293-8146"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyang Chen","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4780","last_page":"4784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9884999990463257,"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":0.7599235773086548},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6089931130409241},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5974473357200623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4029451608657837},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36409634351730347},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.31148022413253784}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7599235773086548},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6089931130409241},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5974473357200623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4029451608657837},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36409634351730347},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.31148022413253784}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-742","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-742","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1899722019","display_name":"\u6df1\u5ea6\u5b66\u4e60\u8bed\u97f3\u8bc6\u522b\u4e2d\u7684\u5feb\u901f\u9ad8\u6548\u81ea\u9002\u5e94\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62071288","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3537961753","display_name":null,"funder_award_id":"62122050","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8721642152","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2950180292","https://openalex.org/W2952361104","https://openalex.org/W2972986505","https://openalex.org/W2998702515","https://openalex.org/W3001197829","https://openalex.org/W3010893827","https://openalex.org/W3015734344","https://openalex.org/W3023351797","https://openalex.org/W3024869864","https://openalex.org/W3033783364","https://openalex.org/W3036224891","https://openalex.org/W3044308976","https://openalex.org/W3095862185","https://openalex.org/W3096918678","https://openalex.org/W3111481301","https://openalex.org/W3159481202","https://openalex.org/W3160397447","https://openalex.org/W3161606033","https://openalex.org/W3163187953","https://openalex.org/W3196649213","https://openalex.org/W3197627775","https://openalex.org/W3202801947","https://openalex.org/W3205500251","https://openalex.org/W4221167533","https://openalex.org/W4285580150","https://openalex.org/W4286981691","https://openalex.org/W4287388854","https://openalex.org/W4287635082","https://openalex.org/W4288020585","https://openalex.org/W4288091954"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W2033914206","https://openalex.org/W1521299571","https://openalex.org/W3162054169","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"For":[0],"self-supervised":[1,106],"speaker":[2,102],"verification,":[3],"the":[4,10,14,18,34,52,57,62,71,81,89,100],"quality":[5],"of":[6,13,75,127],"pseudo":[7],"labels":[8,66],"decides":[9],"upper":[11],"bound":[12],"system":[15,104],"due":[16],"to":[17,32,49,60,68,99],"massive":[19],"unreliable":[20,39,65,72,82],"labels.In":[21,41],"this":[22],"work,":[23],"we":[24,43,79,87],"propose":[25],"dynamic":[26],"loss-gate":[27],"and":[28,55,64,113,117,124],"label":[29,83],"correction":[30],"(DLG-LC)":[31],"alleviate":[33],"performance":[35],"degradation":[36],"caused":[37],"by":[38],"estimated":[40,58],"DLG,":[42],"adopt":[44],"Gaussian":[45],"Mixture":[46],"Model":[47],"(GMM)":[48],"dynamically":[50],"model":[51,85],"loss":[53],"distribution":[54],"use":[56],"GMM":[59],"distinguish":[61],"reliable":[63],"automatically.Besides,":[67],"better":[69],"utilize":[70],"data":[73],"instead":[74],"dropping":[76],"them":[77],"directly,":[78],"correct":[80],"with":[84,105],"predictions.Moreover,":[86],"apply":[88],"negative-pairs-free":[90],"DINO":[91],"framework":[92],"in":[93],"our":[94,108],"experiments":[95],"for":[96],"further":[97],"improvement.Compared":[98],"best-known":[101],"verification":[103],"learning,":[107],"proposed":[109],"DLG-LC":[110],"converges":[111],"faster":[112],"achieves":[114],"11.45%,":[115],"18.35%":[116],"15.16%":[118],"relative":[119],"improvement":[120],"on":[121],"Vox-O,":[122],"Vox-E":[123],"Vox-H":[125],"trials":[126],"Voxceleb1":[128],"evaluation":[129],"dataset.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}