{"id":"https://openalex.org/W2936780106","doi":"https://doi.org/10.1109/icassp.2019.8682259","title":"Cross-lingual Text-independent Speaker Verification Using Unsupervised Adversarial Discriminative Domain Adaptation","display_name":"Cross-lingual Text-independent Speaker Verification Using Unsupervised Adversarial Discriminative Domain Adaptation","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936780106","doi":"https://doi.org/10.1109/icassp.2019.8682259","mag":"2936780106"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/1908.01447","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101861591","display_name":"Wei Xia","orcid":"https://orcid.org/0009-0009-4734-6256"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]},{"id":"https://openalex.org/I4210107838","display_name":"Robust Chip (United States)","ror":"https://ror.org/01rp86637","country_code":"US","type":"company","lineage":["https://openalex.org/I4210107838"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Xia","raw_affiliation_strings":["Center for Robust Speech Systems, UT-Dallas, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, UT-Dallas, TX, USA","institution_ids":["https://openalex.org/I162577319","https://openalex.org/I4210107838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032074795","display_name":"Jing Huang","orcid":"https://orcid.org/0000-0001-8812-2691"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Huang","raw_affiliation_strings":["JD AI Research, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD AI Research, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]},{"id":"https://openalex.org/I4210107838","display_name":"Robust Chip (United States)","ror":"https://ror.org/01rp86637","country_code":"US","type":"company","lineage":["https://openalex.org/I4210107838"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems, UT-Dallas, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, UT-Dallas, TX, USA","institution_ids":["https://openalex.org/I162577319","https://openalex.org/I4210107838"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2644,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.95758553,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5816","last_page":"5820"},"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":0.9934999942779541,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9743000268936157,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8061358332633972},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7178674936294556},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6935858726501465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6141465902328491},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5907847285270691},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5903488993644714},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5862725973129272},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.5538642406463623},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5480688810348511},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5458760857582092},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4921190142631531},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.47464829683303833},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4731624722480774},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45851895213127136},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4526878595352173},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4365268051624298},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.24501848220825195},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07637768983840942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8061358332633972},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7178674936294556},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6935858726501465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6141465902328491},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5907847285270691},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5903488993644714},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5862725973129272},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.5538642406463623},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5480688810348511},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5458760857582092},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4921190142631531},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.47464829683303833},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4731624722480774},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45851895213127136},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4526878595352173},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4365268051624298},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.24501848220825195},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07637768983840942},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/icassp.2019.8682259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1908.01447","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.01447","pdf_url":"https://arxiv.org/pdf/1908.01447","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:1908.01447","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.01447","pdf_url":"https://arxiv.org/pdf/1908.01447","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":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1480629789","https://openalex.org/W1731081199","https://openalex.org/W1936725236","https://openalex.org/W2067301010","https://openalex.org/W2101261946","https://openalex.org/W2107638917","https://openalex.org/W2114925438","https://openalex.org/W2121812409","https://openalex.org/W2162833336","https://openalex.org/W2187089797","https://openalex.org/W2406312423","https://openalex.org/W2413332972","https://openalex.org/W2584329820","https://openalex.org/W2593768305","https://openalex.org/W2746457594","https://openalex.org/W2747900149","https://openalex.org/W2767741204","https://openalex.org/W2788768841","https://openalex.org/W2799508475","https://openalex.org/W2801581493","https://openalex.org/W2802973008","https://openalex.org/W2889278126","https://openalex.org/W2890964092","https://openalex.org/W2962788625","https://openalex.org/W2962914040","https://openalex.org/W2962959915","https://openalex.org/W2963242190","https://openalex.org/W6637618735","https://openalex.org/W6684050148","https://openalex.org/W6713727690","https://openalex.org/W6715601721","https://openalex.org/W6745983287","https://openalex.org/W6748805638","https://openalex.org/W6754448341"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W3141593045","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Speaker":[0],"verification":[1,23,99],"systems":[2],"often":[3],"degrade":[4],"significantly":[5],"when":[6],"there":[7],"is":[8,104,118],"a":[9,86,96],"language":[10],"mismatch":[11],"between":[12],"training":[13,102],"and":[14,36,74,112,114,148,180],"testing":[15],"data.":[16],"Being":[17],"able":[18],"to":[19,54,66,141,186],"improve":[20],"cross-lingual":[21,97],"speaker":[22,98,161,167,173],"system":[24,35,137],"using":[25],"unlabeled":[26],"data":[27,79,103,117,156],"can":[28,169],"greatly":[29],"increase":[30],"the":[31,34,62,67,71,101,115,127,135,165,176,187],"robustness":[32],"of":[33,134,146,158],"reduce":[37],"human":[38],"labeling":[39],"costs.":[40],"In":[41],"this":[42],"study,":[43],"we":[44],"introduce":[45],"an":[46,57],"unsupervised":[47],"Adversarial":[48,89],"Discriminative":[49],"Domain":[50,88],"Adaptation":[51],"(ADDA)":[52],"method":[53],"effectively":[55],"learn":[56],"asymmetric":[58],"mapping":[59],"that":[60,125,164],"adapts":[61],"target":[63,72,177],"domain":[64,73,76,178],"encoder":[65],"source":[68,75],"domain,":[69],"where":[70],"are":[77,93,181],"speech":[78],"from":[80,107,121,139,151],"different":[81],"languages.":[82],"ADDA,":[83],"together":[84],"with":[85,126,184],"popular":[87],"Training":[90],"(DAT)":[91],"approach,":[92],"evaluated":[94],"on":[95,172],"task:":[100],"in":[105,119,189],"English":[106],"NIST":[108],"SRE04-08,":[109],"Mixer":[110],"6":[111],"Switchboard,":[113],"test":[116],"Chinese":[120],"AISHELL-I.":[122],"We":[123],"show":[124],"ADDA":[128,159],"adaptation,":[129],"Equal":[130],"Error":[131],"Rate":[132],"(EER)":[133],"x-vector":[136],"decreases":[138],"9.331%":[140],"7.645%,":[142],"relatively":[143],"18.07%":[144],"reduction":[145,150],"EER,":[147],"6.32%":[149],"DAT":[152],"as":[153],"well.":[154],"Further":[155],"analysis":[157],"adapted":[160],"embedding":[162],"shows":[163],"learned":[166],"embeddings":[168],"perform":[170],"well":[171],"classification":[174],"for":[175],"data,":[179],"less":[182],"dependent":[183],"respect":[185],"shift":[188],"language.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}