{"id":"https://openalex.org/W3038083940","doi":"https://doi.org/10.1109/taslp.2020.3004760","title":"Variational Domain Adversarial Learning With Mutual Information Maximization for Speaker Verification","display_name":"Variational Domain Adversarial Learning With Mutual Information Maximization for Speaker Verification","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3038083940","doi":"https://doi.org/10.1109/taslp.2020.3004760","mag":"3038083940"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3004760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3004760","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":true,"oa_status":"green","oa_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107135/1/Lin_Variational_Domain_Adversarial.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019467579","display_name":"Youzhi Tu","orcid":"https://orcid.org/0000-0002-9580-2414"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Youzhi Tu","raw_affiliation_strings":["Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu City, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu City, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019467579"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":4.5254,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.95480407,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"28","issue":null,"first_page":"2013","last_page":"2024"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9937000274658203,"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":0.9847999811172485,"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":0.762317955493927},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7163798809051514},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.6815351247787476},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5928406119346619},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5692912936210632},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.538212239742279},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5360662341117859},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5135574340820312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5117125511169434},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4960826337337494},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4951910078525543},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4776234030723572},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44296663999557495},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4184926748275757},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4168063998222351},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36379188299179077},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.22719261050224304},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.15225860476493835},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14861813187599182}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.762317955493927},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7163798809051514},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.6815351247787476},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5928406119346619},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5692912936210632},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.538212239742279},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5360662341117859},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5135574340820312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5117125511169434},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4960826337337494},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4951910078525543},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4776234030723572},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44296663999557495},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4184926748275757},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4168063998222351},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36379188299179077},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.22719261050224304},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.15225860476493835},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14861813187599182},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2020.3004760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3004760","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"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/107135","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/107135","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107135/1/Lin_Variational_Domain_Adversarial.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"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":"Journal/Magazine Article"}],"best_oa_location":{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/107135","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/107135","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107135/1/Lin_Variational_Domain_Adversarial.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"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":"Journal/Magazine Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3038083940.pdf","grobid_xml":"https://content.openalex.org/works/W3038083940.grobid-xml"},"referenced_works_count":85,"referenced_works":["https://openalex.org/W866349134","https://openalex.org/W1731081199","https://openalex.org/W1932968309","https://openalex.org/W1959608418","https://openalex.org/W2004497042","https://openalex.org/W2046015436","https://openalex.org/W2067301010","https://openalex.org/W2069739265","https://openalex.org/W2099471712","https://openalex.org/W2121812409","https://openalex.org/W2125865219","https://openalex.org/W2150769028","https://openalex.org/W2168745915","https://openalex.org/W2181594395","https://openalex.org/W2395750323","https://openalex.org/W2403367729","https://openalex.org/W2406312423","https://openalex.org/W2594057160","https://openalex.org/W2775654873","https://openalex.org/W2785519580","https://openalex.org/W2796339975","https://openalex.org/W2796704765","https://openalex.org/W2799976677","https://openalex.org/W2801581493","https://openalex.org/W2803832867","https://openalex.org/W2804397569","https://openalex.org/W2805530975","https://openalex.org/W2807373279","https://openalex.org/W2807546609","https://openalex.org/W2807692250","https://openalex.org/W2888473984","https://openalex.org/W2890964092","https://openalex.org/W2903782687","https://openalex.org/W2910135751","https://openalex.org/W2912298597","https://openalex.org/W2937418893","https://openalex.org/W2962679215","https://openalex.org/W2962690557","https://openalex.org/W2962738009","https://openalex.org/W2962788262","https://openalex.org/W2962928126","https://openalex.org/W2962964508","https://openalex.org/W2963090522","https://openalex.org/W2963104724","https://openalex.org/W2963145887","https://openalex.org/W2963223306","https://openalex.org/W2963382494","https://openalex.org/W2963446838","https://openalex.org/W2963450999","https://openalex.org/W2963987720","https://openalex.org/W2964000524","https://openalex.org/W2964127395","https://openalex.org/W2964168257","https://openalex.org/W2972414786","https://openalex.org/W2972899181","https://openalex.org/W2972956697","https://openalex.org/W2973099347","https://openalex.org/W3015964387","https://openalex.org/W3039832962","https://openalex.org/W4229977739","https://openalex.org/W4248173958","https://openalex.org/W4293568373","https://openalex.org/W4320013936","https://openalex.org/W6610566761","https://openalex.org/W6623950054","https://openalex.org/W6637618735","https://openalex.org/W6640963894","https://openalex.org/W6678814708","https://openalex.org/W6713727690","https://openalex.org/W6734030655","https://openalex.org/W6738543193","https://openalex.org/W6747888389","https://openalex.org/W6748223763","https://openalex.org/W6748391871","https://openalex.org/W6749101112","https://openalex.org/W6750852989","https://openalex.org/W6751660789","https://openalex.org/W6751810238","https://openalex.org/W6752051073","https://openalex.org/W6753417141","https://openalex.org/W6758151150","https://openalex.org/W6758706709","https://openalex.org/W6775957535","https://openalex.org/W6780248173","https://openalex.org/W7036460106"],"related_works":["https://openalex.org/W2785601041","https://openalex.org/W2908598672","https://openalex.org/W2241417046","https://openalex.org/W2053159670","https://openalex.org/W2597403208","https://openalex.org/W4307206503","https://openalex.org/W1983106178","https://openalex.org/W2393900892","https://openalex.org/W2114054925","https://openalex.org/W4306760398"],"abstract_inverted_index":{"Domain":[0],"mismatch":[1,68],"is":[2,37,81,112,181],"a":[3,104],"common":[4],"problem":[5],"in":[6,118,141],"speaker":[7,85,136,178],"verification":[8],"(SV)":[9],"and":[10,69,87,129,148,169],"often":[11],"causes":[12],"performance":[13,30],"degradation.":[14],"For":[15],"the":[16,20,26,29,42,72,76,91,97,110,122,126,130,142,152,155,162,166,173],"system":[17],"relying":[18],"on":[19,41,96,145],"Gaussian":[21,105],"PLDA":[22,77],"backend":[23],"to":[24,65,83,175],"suppress":[25],"channel":[27],"variability,":[28],"would":[31],"be":[32,139],"further":[33],"limited":[34],"if":[35],"there":[36],"no":[38],"Gaussianity":[39,73],"constraint":[40],"learned":[43],"embeddings.":[44],"This":[45],"paper":[46],"proposes":[47],"an":[48,58],"information-maximized":[49],"variational":[50,94],"domain":[51,61,67],"adversarial":[52,62],"neural":[53],"network":[54],"(InfoVDANN)":[55],"that":[56,101,113,134,151,160,180],"incorporates":[57],"InfoVAE":[59,92,111],"into":[60],"training":[63,131],"(DAT)":[64],"reduce":[66],"simultaneously":[70],"meet":[71],"requirement":[74],"of":[75,109],"backend.":[78],"Specifically,":[79],"DAT":[80],"applied":[82],"produce":[84],"discriminative":[86],"domain-invariant":[88],"features,":[89],"while":[90],"performs":[93],"regularization":[95],"embedded":[98,127,167],"features":[99,128,168,171],"so":[100,133],"they":[102],"follow":[103],"distribution.":[106],"Another":[107],"benefit":[108],"it":[114],"avoids":[115],"posterior":[116],"collapse":[117],"VAEs":[119],"by":[120],"preserving":[121],"mutual":[123,163],"information":[124,137,164,179],"between":[125,165],"set":[132],"extra":[135,177],"can":[138],"retained":[140],"features.":[143],"Experiments":[144],"both":[146],"SRE16":[147],"SRE18-CMN2":[149],"show":[150],"InfoVDANN":[153,174],"outperforms":[154],"recent":[156],"VDANN,":[157],"which":[158],"suggests":[159],"increasing":[161],"input":[170],"enables":[172],"extract":[176],"otherwise":[182],"not":[183],"possible.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}