{"id":"https://openalex.org/W4405709681","doi":"https://doi.org/10.1109/iscslp63861.2024.10800140","title":"Prototype and Instance Contrastive Learning for Unsupervised Domain Adaptation in Speaker Verification","display_name":"Prototype and Instance Contrastive Learning for Unsupervised Domain Adaptation in Speaker Verification","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709681","doi":"https://doi.org/10.1109/iscslp63861.2024.10800140"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5004675212","display_name":"Wen Huang","orcid":"https://orcid.org/0000-0001-7682-4354"},"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":true,"raw_author_name":"Wen Huang","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai"],"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070837465","display_name":"Bing Han","orcid":"https://orcid.org/0000-0001-7559-434X"},"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":["AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai"],"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai","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":["AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai"],"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328340","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0003-1523-9631"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]},{"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":["AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai"],"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5004675212"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21936816,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"383","last_page":"387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"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":0.9966999888420105,"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":0.9380999803543091,"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":0.8401321172714233},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6882065534591675},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6307886242866516},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.58244788646698},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5284407138824463},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5096392631530762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48594772815704346},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40882545709609985},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3934803903102875},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06985270977020264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8401321172714233},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6882065534591675},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6307886242866516},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.58244788646698},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5284407138824463},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5096392631530762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48594772815704346},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40882545709609985},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3934803903102875},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06985270977020264},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":34,"referenced_works":["https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2936780106","https://openalex.org/W2962788262","https://openalex.org/W2963040451","https://openalex.org/W2963446838","https://openalex.org/W2963450999","https://openalex.org/W2964154960","https://openalex.org/W2964288524","https://openalex.org/W2972986505","https://openalex.org/W3015301038","https://openalex.org/W3015598461","https://openalex.org/W3015737406","https://openalex.org/W3015964387","https://openalex.org/W3095862185","https://openalex.org/W3097459123","https://openalex.org/W3160646455","https://openalex.org/W3163829335","https://openalex.org/W3197934710","https://openalex.org/W4224917963","https://openalex.org/W4224924624","https://openalex.org/W4224931675","https://openalex.org/W4283008665","https://openalex.org/W4296068790","https://openalex.org/W4297841402","https://openalex.org/W4378696769","https://openalex.org/W4402112094","https://openalex.org/W6631362777","https://openalex.org/W6637131181","https://openalex.org/W6688816777","https://openalex.org/W6768091348","https://openalex.org/W6769178842","https://openalex.org/W6784400926"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W4394775207","https://openalex.org/W4389474468","https://openalex.org/W1521299571","https://openalex.org/W3141593045","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4300172004","https://openalex.org/W2886606195","https://openalex.org/W4252590334"],"abstract_inverted_index":{"Speaker":[0],"verification":[1,75,150],"system":[2],"trained":[3],"on":[4,167],"one":[5,160],"domain":[6,29,36,71],"usually":[7],"suffers":[8],"performance":[9,46,173],"degradation":[10],"when":[11],"applied":[12],"to":[13,90,128,142],"another":[14],"domain.":[15],"To":[16],"address":[17],"this":[18,56],"challenge,":[19],"researchers":[20],"commonly":[21],"use":[22],"feature":[23],"distribution":[24],"matching-based":[25],"methods":[26,42],"in":[27,51,73,159],"unsupervised":[28,70],"adaptation":[30,72],"scenarios":[31],"where":[32],"some":[33],"unlabeled":[34],"target":[35],"data":[37],"is":[38],"available.":[39],"However,":[40],"these":[41],"often":[43],"have":[44,163],"limited":[45],"improvement":[47],"and":[48,61,124,138,145,170],"lack":[49],"generalization":[50,144,179],"various":[52,168],"mismatch":[53],"situations.":[54],"In":[55],"paper,":[57],"we":[58,84,109,162],"propose":[59],"Prototype":[60],"Instance":[62],"Contrastive":[63],"Learning":[64],"(PICL),":[65],"a":[66],"novel":[67],"method":[68],"for":[69],"speaker":[74,149],"through":[76],"dual-level":[77,133],"contrastive":[78,82,107],"learning.":[79],"For":[80,105],"prototype":[81,94],"learning,":[83,108],"generate":[85],"pseudo":[86],"labels":[87],"via":[88],"clustering":[89],"create":[91],"dynamically":[92],"updated":[93],"representations,":[95],"aligning":[96],"instances":[97],"with":[98],"their":[99],"corresponding":[100],"class":[101],"or":[102,116],"cluster":[103],"prototypes.":[104],"instance":[106],"minimize":[110],"the":[111,119,148,178],"distance":[112],"between":[113],"different":[114],"views":[115],"augmentations":[117],"of":[118,147,180],"same":[120],"instance,":[121],"ensuring":[122],"robust":[123],"invariant":[125],"representations":[126],"resilient":[127],"variations":[129],"like":[130],"noise.":[131],"This":[132],"approach":[134],"provides":[135],"both":[136],"high-level":[137],"low-level":[139],"supervision,":[140],"leading":[141],"improved":[143],"robustness":[146],"model.":[151],"Unlike":[152],"previous":[153],"studies":[154],"that":[155],"only":[156],"evaluated":[157],"mismatches":[158],"situation,":[161],"conducted":[164],"relevant":[165],"explorations":[166],"datasets":[169],"achieved":[171],"state-of-the-art":[172],"currently,":[174],"which":[175],"also":[176],"proves":[177],"our":[181],"method.":[182]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}