{"id":"https://openalex.org/W4321780088","doi":"https://doi.org/10.1109/taslp.2023.3244518","title":"Meta-Generalization for Domain-Invariant Speaker Verification","display_name":"Meta-Generalization for Domain-Invariant Speaker Verification","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4321780088","doi":"https://doi.org/10.1109/taslp.2023.3244518"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3244518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3244518","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5016003450","display_name":"Hanyi Zhang","orcid":"https://orcid.org/0000-0002-8523-3481"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hanyi Zhang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","Huiyan Technology (Tianjin) Co., Ltd, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Huiyan Technology (Tianjin) Co., Ltd, Tianjin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457438","display_name":"Meng Liu","orcid":"https://orcid.org/0000-0002-1582-5764"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Liu","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Human-Computer Communications Laboratory (HCCL), Department of Systems Engineering and Engineering Management, Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory (HCCL), Department of Systems Engineering and Engineering Management, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5016003450"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":3.5029,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.9395994,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"1024","last_page":"1036"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9972000122070312,"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":0.9947999715805054,"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/generalization","display_name":"Generalization","score":0.7725799083709717},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7411367893218994},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7295035719871521},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5892421007156372},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5610379576683044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5483803749084473},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4675140976905823},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4146212935447693},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40423962473869324},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3623213768005371},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3374954164028168},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2438029646873474},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18732032179832458},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07962605357170105}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7725799083709717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411367893218994},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7295035719871521},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5892421007156372},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5610379576683044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5483803749084473},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4675140976905823},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4146212935447693},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40423962473869324},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3623213768005371},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3374954164028168},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2438029646873474},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18732032179832458},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07962605357170105},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3244518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3244518","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G7732325329","display_name":null,"funder_award_id":"62176182","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1480629789","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2107638917","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2593649546","https://openalex.org/W2750001021","https://openalex.org/W2752782242","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2887603965","https://openalex.org/W2890964092","https://openalex.org/W2894728917","https://openalex.org/W2916058012","https://openalex.org/W2928165649","https://openalex.org/W2962788262","https://openalex.org/W2963043696","https://openalex.org/W2963446838","https://openalex.org/W2964105864","https://openalex.org/W2972315886","https://openalex.org/W2972552635","https://openalex.org/W2981817257","https://openalex.org/W3010925296","https://openalex.org/W3015443711","https://openalex.org/W3015503328","https://openalex.org/W3024869864","https://openalex.org/W3035067471","https://openalex.org/W3035436173","https://openalex.org/W3049278490","https://openalex.org/W3092053846","https://openalex.org/W3094665028","https://openalex.org/W3095799614","https://openalex.org/W3095992690","https://openalex.org/W3096235116","https://openalex.org/W3097224504","https://openalex.org/W3103152812","https://openalex.org/W3108145393","https://openalex.org/W3134299941","https://openalex.org/W3147324749","https://openalex.org/W3154934604","https://openalex.org/W3160309283","https://openalex.org/W3160744627","https://openalex.org/W3167533889","https://openalex.org/W4206908380","https://openalex.org/W4224927738","https://openalex.org/W4289639938","https://openalex.org/W4289750118","https://openalex.org/W6639480849","https://openalex.org/W6681968150","https://openalex.org/W6717697761","https://openalex.org/W6720057410","https://openalex.org/W6734652334","https://openalex.org/W6736057607","https://openalex.org/W6747943641","https://openalex.org/W6753575415","https://openalex.org/W6754038005","https://openalex.org/W6755310938","https://openalex.org/W6763275521","https://openalex.org/W6768532476","https://openalex.org/W6772329248","https://openalex.org/W6774827837","https://openalex.org/W6785863445"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W2075445622","https://openalex.org/W2053159670"],"abstract_inverted_index":{"Automatic":[0],"speaker":[1,78,121,211],"verification":[2,79,122],"(ASV)":[3],"exhibits":[4],"unsatisfactory":[5],"performance":[6,33,178,204],"under":[7,34],"domain":[8,37,51,138,160,207],"mismatch":[9,139,208],"conditions":[10],"owing":[11],"to":[12,63,68,94,134,169,173],"intrinsic":[13],"and":[14,23,50,90,102,119,130,191],"extrinsic":[15],"factors,":[16],"such":[17],"as":[18,150,155],"variations":[19],"in":[20,27,53,205,210],"speaking":[21],"styles":[22],"recording":[24],"devices":[25],"encountered":[26],"real-world":[28],"applications.":[29],"To":[30],"ensure":[31],"robust":[32],"unseen":[35,111,181],"conditions,":[36],"generalization":[38,105,161],"has":[39,167],"been":[40],"explored.":[41],"However,":[42],"an":[43],"inherent":[44],"contradiction":[45],"exists":[46],"between":[47,100],"model":[48,109,166,177],"discrimination":[49,56],"generalization,":[52],"which":[54],"the":[55,76,97,104,108,136,151,159,165,176,180,183],"ability":[57,106],"may":[58],"be":[59],"reduced":[60],"while":[61],"learning":[62],"generalize.":[64],"In":[65,113],"this":[66],"paper,":[67],"extract":[69],"discriminative":[70],"yet":[71],"domain-invariant":[72],"representations,":[73],"we":[74,84,115],"propose":[75,85],"meta-generalized":[77],"(MGSV)":[80],"via":[81],"meta-learning.":[82],"Specifically,":[83],"a":[86,91],"metric-based":[87],"distribution":[88],"optimization":[89],"gradient-based":[92],"meta-optimization":[93],"simultaneously":[95],"supervise":[96],"spatial":[98],"relationship":[99],"embeddings":[101],"improve":[103],"of":[107],"on":[110,127,179,188],"domains.":[112],"addition,":[114],"design":[116],"multiple-single":[117],"(MS)":[118],"simulated":[120],"(SSV)":[123],"sampling":[124],"strategies":[125,133],"based":[126],"single-domain":[128],"(SD)":[129],"single-single":[131],"(SS)":[132],"simulate":[135],"train/test":[137],"more":[140],"relevantly,":[141],"thereby":[142],"mining":[143],"transferable":[144],"speaker-related":[145],"knowledge.":[146],"SSV":[147],"is":[148,186],"chosen":[149],"most":[152],"effective":[153],"method,":[154],"it":[156],"substantially":[157],"improves":[158],"by":[162],"ensuring":[163],"that":[164,198],"learned":[168],"discriminate":[170],"efficiently.":[171],"Additionally,":[172],"intuitively":[174],"reflect":[175],"domains,":[182],"proposed":[184,200],"method":[185,201],"validated":[187],"cross-genre,":[189],"cross-device,":[190],"cross-dataset":[192],"tasks.":[193],"The":[194],"experimental":[195],"results":[196],"demonstrate":[197],"our":[199],"achieves":[202],"remarkable":[203],"handling":[206],"issues":[209],"verification.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}