{"id":"https://openalex.org/W3096127734","doi":"https://doi.org/10.1109/taslp.2020.3030499","title":"A Framework for Adapting DNN Speaker Embedding Across Languages","display_name":"A Framework for Adapting DNN Speaker Embedding Across Languages","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3096127734","doi":"https://doi.org/10.1109/taslp.2020.3030499","mag":"3096127734"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3030499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3030499","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/10397/107121/1/Lin_Framework_Adapting_Dnn.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090644975","display_name":"Weiwei Lin","orcid":"https://orcid.org/0000-0002-9241-0271"},"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":"Weiwei Lin","raw_affiliation_strings":["Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, hung hom, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, hung hom, Hong Kong","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, hung hom, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, hung hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368048","display_name":"Na Li","orcid":"https://orcid.org/0000-0001-9545-3050"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Na Li","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, United States","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, United States","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, United States","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4341,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86146883,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"28","issue":null,"first_page":"2810","last_page":"2822"},"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":0.9944999814033508,"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":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7750962972640991},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7452678084373474},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7072299718856812},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6169703006744385},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5604037046432495},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5504804253578186},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.49279382824897766},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4694019854068756},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.450679749250412},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4357711672782898},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43230000138282776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4063985347747803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7750962972640991},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7452678084373474},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7072299718856812},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6169703006744385},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5604037046432495},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5504804253578186},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.49279382824897766},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4694019854068756},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.450679749250412},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4357711672782898},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43230000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4063985347747803},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/taslp.2020.3030499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3030499","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:10397/107121","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/107121","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107121/1/Lin_Framework_Adapting_Dnn.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:10397/107121","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/107121","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107121/1/Lin_Framework_Adapting_Dnn.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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3096127734.pdf"},"referenced_works_count":69,"referenced_works":["https://openalex.org/W1487641199","https://openalex.org/W1522301498","https://openalex.org/W1617650991","https://openalex.org/W1731081199","https://openalex.org/W1959608418","https://openalex.org/W1976637928","https://openalex.org/W2002342963","https://openalex.org/W2010023285","https://openalex.org/W2037740282","https://openalex.org/W2112552549","https://openalex.org/W2125865219","https://openalex.org/W2146871184","https://openalex.org/W2156557681","https://openalex.org/W2159291411","https://openalex.org/W2159786793","https://openalex.org/W2395750323","https://openalex.org/W2402146185","https://openalex.org/W2404617565","https://openalex.org/W2584886900","https://openalex.org/W2587088898","https://openalex.org/W2590953969","https://openalex.org/W2617322972","https://openalex.org/W2622599113","https://openalex.org/W2696967604","https://openalex.org/W2735780771","https://openalex.org/W2739748921","https://openalex.org/W2747476845","https://openalex.org/W2748665871","https://openalex.org/W2756073160","https://openalex.org/W2787273235","https://openalex.org/W2807246346","https://openalex.org/W2807373279","https://openalex.org/W2888473984","https://openalex.org/W2890964092","https://openalex.org/W2942203175","https://openalex.org/W2962788262","https://openalex.org/W2962892300","https://openalex.org/W2962976271","https://openalex.org/W2963364041","https://openalex.org/W2963446712","https://openalex.org/W2963446838","https://openalex.org/W2963450999","https://openalex.org/W2964121744","https://openalex.org/W2964288524","https://openalex.org/W2970971581","https://openalex.org/W2973099347","https://openalex.org/W2981022124","https://openalex.org/W2988989211","https://openalex.org/W3015301038","https://openalex.org/W3015964387","https://openalex.org/W3035743198","https://openalex.org/W4250482878","https://openalex.org/W4295312788","https://openalex.org/W6629354409","https://openalex.org/W6631190155","https://openalex.org/W6636267554","https://openalex.org/W6637618735","https://openalex.org/W6640963894","https://openalex.org/W6676726796","https://openalex.org/W6678814708","https://openalex.org/W6683633756","https://openalex.org/W6712930963","https://openalex.org/W6737965738","https://openalex.org/W6741832134","https://openalex.org/W6748480929","https://openalex.org/W6761827036","https://openalex.org/W6766978945","https://openalex.org/W6771245373","https://openalex.org/W6775957535"],"related_works":["https://openalex.org/W2162634028","https://openalex.org/W2400341349","https://openalex.org/W2336335760","https://openalex.org/W2970987681","https://openalex.org/W2364099918","https://openalex.org/W3041732398","https://openalex.org/W2594231800","https://openalex.org/W2056119007","https://openalex.org/W2045259680","https://openalex.org/W2516800609"],"abstract_inverted_index":{"Language":[0],"mismatch":[1],"remains":[2],"a":[3,53,196],"major":[4],"hindrance":[5],"to":[6,82,195],"the":[7,35,43,83,108,112,128,158,174,186],"extensive":[8],"deployment":[9],"of":[10,46,142,203],"speaker":[11,36,66],"verification":[12],"(SV)":[13],"systems.":[14],"Current":[15],"language":[16],"adaptation":[17,30,118,162,188],"methods":[18],"in":[19,26,114,127,146,189,207],"SV":[20],"mainly":[21],"rely":[22],"on":[23],"linear":[24],"projection":[25],"embedding":[27,67],"space;":[28],"i.e.,":[29],"is":[31],"carried":[32],"out":[33],"after":[34],"embeddings":[37],"have":[38],"been":[39],"created,":[40],"which":[41,153],"underutilizes":[42],"powerful":[44],"representation":[45],"deep":[47,62],"neural":[48,63],"networks.":[49],"This":[50],"article":[51],"proposes":[52],"maximum":[54],"mean":[55],"discrepancy":[56,93],"(MMD)":[57],"based":[58],"framework":[59,84,165,176,194],"for":[60],"adapting":[61],"network":[64],"(DNN)":[65],"across":[68],"languages,":[69],"featuring":[70],"multi-level":[71],"domain":[72,92],"loss,":[73],"separate":[74],"batch":[75,115],"normalization,":[76],"and":[77,97,120,144,150,205,211],"consistency":[78,132],"regularization.":[79,133],"We":[80,87],"refer":[81],"as":[85],"MSC.":[86],"show":[88],"that":[89],"(1)":[90],"minimizing":[91],"at":[94,103],"both":[95],"frame-":[96],"utterance-levels":[98],"performs":[99],"significantly":[100,155],"better":[101,156],"than":[102,157],"utterance-level":[104],"alone;":[105],"(2)":[106],"separating":[107],"source-domain":[109],"data":[110,122],"from":[111],"target-domain":[113,130],"normalization":[116],"improves":[117],"performance;":[119],"(3)":[121],"augmentation":[123],"can":[124],"be":[125],"utilized":[126],"unlabelled":[129],"through":[131],"By":[134,172],"combining":[135,173],"these":[136],"findings,":[137],"we":[138,180,199],"achieve":[139,181],"an":[140,182,201],"EER":[141,202],"8.69%":[143],"7.95%":[145],"NIST":[147,208],"SRE":[148,209],"2016":[149,210],"2018,":[151,212],"respectively,":[152],"are":[154],"previously":[159],"proposed":[160,175],"DNN":[161],"methods.":[163],"Our":[164],"also":[166],"works":[167],"well":[168],"with":[169,177],"backend":[170,178,187],"adaptation.":[171],"adaptation,":[179],"11.8%":[183],"improvement":[184],"over":[185],"SRE18.":[190],"When":[191],"applying":[192],"our":[193],"121-layer":[197],"Densenet,":[198],"achieved":[200],"7.81%":[204],"7.02%":[206],"respectively.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}