{"id":"https://openalex.org/W4385478165","doi":"https://doi.org/10.1109/icasspw59220.2023.10192957","title":"Improving Dino-Based Self-Supervised Speaker Verification with Progressive Cluster-Aware Training","display_name":"Improving Dino-Based Self-Supervised Speaker Verification with Progressive Cluster-Aware Training","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385478165","doi":"https://doi.org/10.1109/icasspw59220.2023.10192957"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10192957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10192957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5100690517","display_name":"Bing Han","orcid":"https://orcid.org/0000-0002-6319-6755"},"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":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100566827","display_name":"Wen Huang","orcid":"https://orcid.org/0000-0001-8324-2416"},"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":"Wen Huang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, 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":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, 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":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, 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":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9968000054359436,"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":0.994700014591217,"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":0.7960182428359985},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7862421274185181},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7373964786529541},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6325973868370056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5879872441291809},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.558881938457489},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4875044524669647},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.4798009693622589},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4781721234321594},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44876691699028015},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.41866976022720337},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3511356711387634},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3442763686180115},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07229900360107422}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7960182428359985},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7862421274185181},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7373964786529541},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6325973868370056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5879872441291809},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.558881938457489},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4875044524669647},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4798009693622589},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4781721234321594},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44876691699028015},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.41866976022720337},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3511356711387634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3442763686180115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07229900360107422},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10192957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10192957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2114925438","https://openalex.org/W2219249508","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2972705840","https://openalex.org/W3010925296","https://openalex.org/W3015598461","https://openalex.org/W3015734344","https://openalex.org/W3023351797","https://openalex.org/W3024869864","https://openalex.org/W3033783364","https://openalex.org/W3036601975","https://openalex.org/W3044308976","https://openalex.org/W3135006803","https://openalex.org/W3159481202","https://openalex.org/W3160397447","https://openalex.org/W3161606033","https://openalex.org/W3178307467","https://openalex.org/W3198275944","https://openalex.org/W3205310163","https://openalex.org/W3206189675","https://openalex.org/W3209059054","https://openalex.org/W4287635082","https://openalex.org/W4288091954","https://openalex.org/W4290712827","https://openalex.org/W4290995108","https://openalex.org/W4296068770","https://openalex.org/W4319862473","https://openalex.org/W6688816777","https://openalex.org/W6740167877","https://openalex.org/W6769178842","https://openalex.org/W6773803412","https://openalex.org/W6779230768","https://openalex.org/W6780218876","https://openalex.org/W6781368565","https://openalex.org/W6784330115","https://openalex.org/W6787335539"],"related_works":["https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W1999699871","https://openalex.org/W2786391746","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2033669961","https://openalex.org/W3132346564","https://openalex.org/W2991483587","https://openalex.org/W1972167985"],"abstract_inverted_index":{"Self-supervised":[0],"contrastive":[1],"learning":[2],"has":[3],"recently":[4],"emerged":[5],"as":[6,112,114],"one":[7],"of":[8,51,108,135,142],"the":[9,25,42,49,60,81,90,101,123,133,154],"promising":[10],"approaches":[11],"in":[12,41,89,100],"speaker":[13,43],"verification":[14,44],"task,":[15],"due":[16],"to":[17,62,65,79],"its":[18],"independence":[19],"from":[20,86,95],"labeled":[21,143,151],"data.":[22,144,161],"Among":[23],"them,":[24],"DINO-based":[26],"self-supervised":[27],"framework,":[28],"trained":[29,158],"without":[30],"exploiting":[31],"negative":[32],"pairs,":[33],"is":[34],"very":[35],"popular":[36],"and":[37],"achieves":[38,122],"excellent":[39],"performance":[40],"task.":[45],"However,":[46],"limited":[47],"by":[48],"duration":[50],"utterance,":[52],"there":[53],"exist":[54],"many":[55],"overlaps":[56],"which":[57],"may":[58],"mislead":[59],"model":[61,82,147],"pay":[63],"attention":[64],"irrelevant":[66],"information.":[67],"To":[68],"tackle":[69],"this":[70],"problem,":[71],"we":[72,104,131],"propose":[73],"a":[74,96,139],"cluster-aware":[75],"(CA)":[76],"training":[77],"strategy":[78],"make":[80],"crop":[83],"positive":[84],"segments":[85],"several":[87],"utterances":[88],"same":[91],"cluster":[92],"rather":[93],"than":[94],"single":[97],"utterance.":[98],"Besides,":[99],"clustering":[102,111],"stage,":[103],"also":[105],"investigate":[106],"strategies":[107],"fixed":[109],"number":[110],"well":[113],"progressive":[115],"clustering.":[116],"With":[117],"these":[118],"strategies,":[119],"our":[120],"CA-DINO":[121,137],"state-of-the-art":[124],"result":[125],"on":[126,159],"Vox-O":[127],"test":[128],"set.":[129],"Finally,":[130],"explore":[132],"effect":[134],"fine-tuning":[136],"with":[138,148],"small":[140],"amount":[141],"Our":[145],"proposed":[146],"only":[149],"10%":[150],"data":[152],"outperforms":[153],"fully":[155],"supervised":[156],"system":[157],"all":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}