{"id":"https://openalex.org/W3205335446","doi":"https://doi.org/10.1109/icassp43922.2022.9746210","title":"Tackling the Score Shift in Cross-Lingual Speaker Verification by Exploiting Language Information","display_name":"Tackling the Score Shift in Cross-Lingual Speaker Verification by Exploiting Language Information","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3205335446","doi":"https://doi.org/10.1109/icassp43922.2022.9746210","mag":"3205335446"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746210","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/2110.09150","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022199264","display_name":"Jenthe Thienpondt","orcid":"https://orcid.org/0000-0001-5990-722X"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jenthe Thienpondt","raw_affiliation_strings":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032699386","display_name":"Brecht Desplanques","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Brecht Desplanques","raw_affiliation_strings":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046536366","display_name":"Kris Demuynck","orcid":"https://orcid.org/0000-0001-8525-7160"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kris Demuynck","raw_affiliation_strings":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7187","last_page":"7191"},"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":0.998199999332428,"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":0.9861999750137329,"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":0.8194151520729065},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7217016220092773},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6607092022895813},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5608747005462646},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5182466506958008},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4582272469997406},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45558154582977295},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.436176598072052},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4339723289012909},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4325729310512543},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.41305744647979736},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37331050634384155},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22423073649406433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8194151520729065},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7217016220092773},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6607092022895813},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5608747005462646},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5182466506958008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4582272469997406},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45558154582977295},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.436176598072052},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4339723289012909},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4325729310512543},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41305744647979736},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37331050634384155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22423073649406433},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746210","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2110.09150","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.09150","pdf_url":"https://arxiv.org/pdf/2110.09150","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},{"id":"pmh:oai:archive.ugent.be:8756347","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-8756347","pdf_url":"https://biblio.ugent.be/publication/8756347/file/8756350.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781665405409","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.09150","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.09150","pdf_url":"https://arxiv.org/pdf/2110.09150","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W125553504","https://openalex.org/W1522301498","https://openalex.org/W1965555277","https://openalex.org/W2170088868","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2938358845","https://openalex.org/W2964054038","https://openalex.org/W2964121744","https://openalex.org/W2969985801","https://openalex.org/W3024541814","https://openalex.org/W3024869864","https://openalex.org/W3094374485","https://openalex.org/W3103152812","https://openalex.org/W3139878283","https://openalex.org/W3141035251","https://openalex.org/W3197055177","https://openalex.org/W3198397427","https://openalex.org/W3198698812","https://openalex.org/W4286981691","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6784400926","https://openalex.org/W6801723603"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4235705411","https://openalex.org/W1996621592","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W3094374485","https://openalex.org/W3096066489"],"abstract_inverted_index":{"This":[0],"paper":[1],"contains":[2],"a":[3,79,116,126],"post-challenge":[4],"performance":[5],"analysis":[6],"on":[7,50,110,134],"cross-lingual":[8,36,63,89],"speaker":[9,27,32,64],"verification":[10,65],"of":[11,53,87,115],"the":[12,16,39,51,85,92,100,131,135,147],"IDLab":[13],"submission":[14],"to":[15,61,141],"VoxCeleb":[17],"Speaker":[18],"Recognition":[19],"Challenge":[20],"2021":[21],"(VoxSRC-21).":[22],"We":[23,57,105],"show":[24],"that":[25],"current":[26],"embedding":[28],"extractors":[29],"consistently":[30],"underestimate":[31],"similarity":[33],"in":[34,99,125,146],"within-speaker":[35],"trials.":[37],"Consequently,":[38],"typical":[40],"training":[41,76],"and":[42,112,139],"scoring":[43],"protocols":[44],"do":[45],"not":[46],"put":[47],"enough":[48],"emphasis":[49],"compensation":[52],"intra-speaker":[54,88],"language":[55,97,118],"variability.":[56],"propose":[58],"two":[59],"techniques":[60,123],"increase":[62],"robustness.":[66],"First,":[67],"we":[68,95],"enhance":[69],"our":[70,142],"previously":[71],"proposed":[72,122],"Large-Margin":[73],"Fine-Tuning":[74],"(LM-FT)":[75],"stage":[77],"with":[78],"mini-batch":[80],"sampling":[81],"strategy":[82],"which":[83],"increases":[84],"amount":[86],"samples":[90],"within":[91],"mini-batch.":[93],"Second,":[94],"incorporate":[96],"information":[98],"logistic":[101],"regression":[102],"calibration":[103],"stage.":[104],"integrate":[106],"quality":[107],"metrics":[108],"based":[109],"soft":[111],"hard":[113],"decisions":[114],"VoxLingua107":[117],"identification":[119],"model.":[120],"The":[121],"result":[124],"11.7%":[127],"relative":[128],"improvement":[129],"over":[130],"baseline":[132],"model":[133],"VoxSRC-21":[136],"test":[137],"set":[138],"contributed":[140],"third":[143],"place":[144],"finish":[145],"corresponding":[148],"challenge.":[149]},"counts_by_year":[{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-10-25T00:00:00"}