{"id":"https://openalex.org/W3160646455","doi":"https://doi.org/10.1109/icassp39728.2021.9414261","title":"Self-Supervised Learning Based Domain Adaptation for Robust Speaker Verification","display_name":"Self-Supervised Learning Based Domain Adaptation for Robust Speaker Verification","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160646455","doi":"https://doi.org/10.1109/icassp39728.2021.9414261","mag":"3160646455"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.13843","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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 SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328272","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-1595-3619"},"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":"Shuai Wang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, 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 SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, 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":41,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5834","last_page":"5838"},"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":0.9851999878883362,"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":0.9731000065803528,"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":0.8385816812515259},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8056058883666992},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6925321221351624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6355100870132446},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6010265350341797},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4517190456390381},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43820616602897644},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43809252977371216},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42925018072128296},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4286068081855774},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07381477952003479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8385816812515259},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8056058883666992},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6925321221351624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6355100870132446},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6010265350341797},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4517190456390381},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43820616602897644},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43809252977371216},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42925018072128296},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4286068081855774},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07381477952003479},{"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/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.13843","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.13843","pdf_url":"https://arxiv.org/pdf/2108.13843","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:2108.13843","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.13843","pdf_url":"https://arxiv.org/pdf/2108.13843","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":0.5400000214576721,"id":"https://metadata.un.org/sdg/10"},{"display_name":"Peace, Justice and strong institutions","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1006777433","https://openalex.org/W1524333225","https://openalex.org/W2181594395","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2794506738","https://openalex.org/W2798991696","https://openalex.org/W2799508475","https://openalex.org/W2888968865","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2936780106","https://openalex.org/W2949526695","https://openalex.org/W2951534110","https://openalex.org/W2962788262","https://openalex.org/W2962788625","https://openalex.org/W2963450999","https://openalex.org/W2969985801","https://openalex.org/W2972369255","https://openalex.org/W2972414786","https://openalex.org/W2981087920","https://openalex.org/W2981461916","https://openalex.org/W3005680577","https://openalex.org/W3010925296","https://openalex.org/W3013020904","https://openalex.org/W3015598461","https://openalex.org/W3035524453","https://openalex.org/W3095862185","https://openalex.org/W4288091954","https://openalex.org/W6631362777","https://openalex.org/W6769178842","https://openalex.org/W6774314701","https://openalex.org/W6784756737"],"related_works":["https://openalex.org/W4389474468","https://openalex.org/W4283211831","https://openalex.org/W2129767422","https://openalex.org/W3210196349","https://openalex.org/W4214728004","https://openalex.org/W4300172004","https://openalex.org/W2950181282","https://openalex.org/W3035557009","https://openalex.org/W3203792196","https://openalex.org/W2798287483"],"abstract_inverted_index":{"Large":[0],"performance":[1,39,65],"degradation":[2],"is":[3],"often":[4],"observed":[5],"for":[6],"speaker":[7,119,161],"verification":[8],"systems":[9],"when":[10],"applied":[11],"to":[12,36,79,96],"a":[13,87],"new":[14,102],"domain":[15,23,44,58,82,91,115,124],"dataset.":[16],"Given":[17],"an":[18],"unlabeled":[19],"target-domain":[20],"dataset,":[21],"unsupervised":[22,81],"adaptation":[24,83,92],"(UDA)":[25],"methods,":[26],"which":[27,165],"usually":[28],"leverage":[29,108],"adversarial":[30,48],"training":[31,49,104],"strategies,":[32],"are":[33],"commonly":[34],"used":[35],"bridge":[37],"the":[38,43,53,64,68,80,97,101,109,118,128,132,144,155,169],"gap":[40],"caused":[41],"by":[42],"mismatch.":[45],"However,":[46],"such":[47],"strategy":[50,78,105],"only":[51],"uses":[52],"distribution":[54],"information":[55,112],"of":[56],"target":[57,69,114,140],"data":[59],"and":[60,85,116,137,143],"can":[61,106,167],"not":[62],"ensure":[63],"improvement":[66],"on":[67,131,154,163,172],"domain.":[70],"In":[71],"this":[72,173],"paper,":[73],"we":[74],"incorporate":[75],"self-supervised":[76,88],"learning":[77,89],"system":[84,147],"proposed":[86,129],"based":[90],"approach":[93,130],"(SSDA).":[94],"Compared":[95],"traditional":[98],"UDA":[99],"method,":[100],"SSDA":[103,146],"fully":[107],"potential":[110],"label":[111],"from":[113,122],"adapt":[117],"discrimination":[120],"ability":[121],"source":[123,135],"simultaneously.":[125],"We":[126],"evaluated":[127],"Vox-Celeb":[133],"(labeled":[134],"domain)":[136,141],"CnCeleb":[138,156],"(unlabeled":[139],"datasets,":[142],"best":[145],"obtains":[148],"10.2%":[149],"Equal":[150],"Error":[151],"Rate":[152],"(EER)":[153],"dataset":[157],"without":[158],"using":[159],"any":[160],"labels":[162],"CnCeleb,":[164],"also":[166],"achieve":[168],"state-of-the-art":[170],"results":[171],"corpus.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2021-05-24T00:00:00"}