{"id":"https://openalex.org/W4392904642","doi":"https://doi.org/10.1109/icassp48485.2024.10446444","title":"Robust Cross-Domain Speaker Verification with Multi-Level Domain Adapters","display_name":"Robust Cross-Domain Speaker Verification with Multi-Level Domain Adapters","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904642","doi":"https://doi.org/10.1109/icassp48485.2024.10446444"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","AI Institute Department of Computer Science and Engineering, Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"AI Institute Department of Computer Science and Engineering, Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","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,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","AI Institute Department of Computer Science and Engineering, Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"AI Institute Department of Computer Science and Engineering, Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","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":["The Chinese University of Hong Kong,Shenzhen Research Institute of Big Data,Shenzhen,China","Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I4210116924"]}]},{"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,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","AI Institute Department of Computer Science and Engineering, Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"AI Institute Department of Computer Science and Engineering, Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence, 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,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","AI Institute Department of Computer Science and Engineering, Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"AI Institute Department of Computer Science and Engineering, Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11781","last_page":"11785"},"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":0.9955000281333923,"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":0.9926000237464905,"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":0.8107186555862427},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.7154090404510498},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6734694242477417},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6056118011474609},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5324624180793762},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.511576235294342},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.49365124106407166},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4820195436477661},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40756505727767944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8107186555862427},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.7154090404510498},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6734694242477417},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6056118011474609},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5324624180793762},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.511576235294342},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.49365124106407166},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4820195436477661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40756505727767944},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/G4532141107","display_name":null,"funder_award_id":"21511101100","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G5465080215","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"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/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"},{"id":"https://openalex.org/F4320333998","display_name":"Shenzhen Research Institute, City University of Hong Kong","ror":"https://ror.org/00xc0ma20"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1006777433","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2962788262","https://openalex.org/W2963386851","https://openalex.org/W2963446838","https://openalex.org/W2969985801","https://openalex.org/W2973099347","https://openalex.org/W2981087920","https://openalex.org/W3010925296","https://openalex.org/W3015546017","https://openalex.org/W3015598461","https://openalex.org/W3015737406","https://openalex.org/W3095862185","https://openalex.org/W3097470351","https://openalex.org/W4286981691","https://openalex.org/W4288091954","https://openalex.org/W4296068606","https://openalex.org/W4382602944","https://openalex.org/W4385822954","https://openalex.org/W4385823321","https://openalex.org/W6639480849","https://openalex.org/W6688816777","https://openalex.org/W6769178842","https://openalex.org/W6784400926","https://openalex.org/W6853723667"],"related_works":["https://openalex.org/W112947718","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W1998549096","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489"],"abstract_inverted_index":{"Speaker":[0],"verification":[1],"encounters":[2],"significant":[3],"challenges":[4],"when":[5],"confronted":[6],"with":[7,45,84,124],"diverse":[8,62],"domain":[9,18,111,118,125],"data,":[10,47],"often":[11],"resulting":[12],"in":[13,23],"performance":[14,22,83],"degradation":[15],"due":[16],"to":[17,73,91],"mismatch.":[19],"To":[20],"enhance":[21],"cross-domain":[24,82],"scenarios,":[25],"we":[26,98],"introduce":[27],"the":[28,58,102,114,135],"Domain":[29],"Adapter,":[30],"an":[31],"adaptable":[32,72],"module":[33,39,79],"designed":[34],"for":[35,110],"specific":[36],"domains.":[37,63,94],"This":[38],"learns":[40],"and":[41,51,70,113,130],"integrates":[42],"domain-specific":[43],"information":[44],"speaker-related":[46],"mitigating":[48],"domain-related":[49],"variations":[50],"promoting":[52],"convergence":[53],"of":[54,117],"utterance":[55],"embeddings":[56],"from":[57],"same":[59],"speaker":[60],"across":[61,67,137],"It":[64],"offers":[65],"configurability":[66],"multiple":[68],"levels":[69],"is":[71],"various":[74],"backbone":[75],"architectures.":[76],"Our":[77],"proposed":[78],"substantially":[80],"enhances":[81],"minimal":[85],"parameter":[86],"increments":[87],"while":[88],"effectively":[89],"generalizing":[90],"previously":[92],"unseen":[93],"In":[95],"our":[96],"experiments,":[97],"present":[99],"results":[100],"on":[101],"3D-Speaker":[103,139],"dataset,":[104],"which":[105],"provides":[106],"acoustically-relevant":[107],"attributes":[108],"crucial":[109],"categorization":[112],"subsequent":[115],"learning":[116],"information.":[119],"The":[120],"top-performing":[121],"system":[122],"integrated":[123],"adapters":[126],"achieved":[127],"10.8%,":[128],"14.8%,":[129],"21.1%":[131],"EER":[132],"improvements":[133],"over":[134],"baseline":[136],"three":[138],"dataset":[140],"trials.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}