{"id":"https://openalex.org/W3094374485","doi":"https://doi.org/10.1109/icassp39728.2021.9414600","title":"The Idlab Voxsrc-20 Submission: Large Margin Fine-Tuning and Quality-Aware Score Calibration in DNN Based Speaker Verification","display_name":"The Idlab Voxsrc-20 Submission: Large Margin Fine-Tuning and Quality-Aware Score Calibration in DNN Based Speaker Verification","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3094374485","doi":"https://doi.org/10.1109/icassp39728.2021.9414600","mag":"3094374485"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/2010.11255","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab, Department of Electronics and Information Systems,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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab, Department of Electronics and Information Systems,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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab, Department of Electronics and Information Systems,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":54,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5814","last_page":"5818"},"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":0.9976000189781189,"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":0.9932000041007996,"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/margin","display_name":"Margin (machine learning)","score":0.9006854891777039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8130974173545837},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.7420745491981506},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.722298264503479},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5259870886802673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48840564489364624},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4810483753681183},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47958412766456604},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4730647802352905},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3621532917022705},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32464051246643066},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06893831491470337},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06129443645477295}],"concepts":[{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.9006854891777039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8130974173545837},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.7420745491981506},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.722298264503479},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5259870886802673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48840564489364624},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4810483753681183},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47958412766456604},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4730647802352905},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3621532917022705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32464051246643066},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06893831491470337},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06129443645477295},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.11255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11255","pdf_url":"https://arxiv.org/pdf/2010.11255","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:8713072","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/8713072","pdf_url":"http://hdl.handle.net/1854/LU-8713072","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: 9781728176055","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.11255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11255","pdf_url":"https://arxiv.org/pdf/2010.11255","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":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W125553504","https://openalex.org/W143396524","https://openalex.org/W1522301498","https://openalex.org/W1589137271","https://openalex.org/W2057888214","https://openalex.org/W2117671523","https://openalex.org/W2170088868","https://openalex.org/W2173629880","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2485395001","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747476845","https://openalex.org/W2752782242","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2928165649","https://openalex.org/W2936774411","https://openalex.org/W2938358845","https://openalex.org/W2962922273","https://openalex.org/W2963420686","https://openalex.org/W2964054038","https://openalex.org/W2964121744","https://openalex.org/W2969985801","https://openalex.org/W2973032144","https://openalex.org/W3024541814","https://openalex.org/W3024869864","https://openalex.org/W3042801391","https://openalex.org/W3093582452","https://openalex.org/W3111481301","https://openalex.org/W4286981691","https://openalex.org/W4309845474","https://openalex.org/W6631190155","https://openalex.org/W6635152626","https://openalex.org/W6688816777","https://openalex.org/W6784400926","https://openalex.org/W6787439801"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W3162054169","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"propose":[4],"and":[5,12,107,132],"analyse":[6],"a":[7,13,25,61,69],"large":[8],"margin":[9,22,64],"fine-tuning":[10,23],"strategy":[11],"quality-aware":[14],"score":[15],"calibration":[16,67,96],"in":[17,58,72,94,138],"text-independent":[18],"speaker":[19,32,48,73],"verification.":[20],"Large":[21],"is":[24,68],"secondary":[26],"training":[27,56],"stage":[28],"for":[29],"DNN":[30],"based":[31],"verification":[33,74,141],"systems":[34,75],"trained":[35],"with":[36,60],"margin-based":[37],"loss":[38],"functions.":[39],"It":[40],"enables":[41],"the":[42,52,95,98,102,118,139,144],"network":[43],"to":[44,76,80,87,122,134],"create":[45],"more":[46,62,108],"robust":[47],"embeddings":[49],"by":[50],"enabling":[51],"use":[53],"of":[54,101,143],"longer":[55],"utterances":[57],"combination":[59],"aggressive":[63],"penalty.":[65],"Score":[66],"common":[70],"practice":[71],"map":[77],"output":[78],"scores":[79],"well-calibrated":[81],"log-likelihood-ratios,":[82],"which":[83],"can":[84],"be":[85],"converted":[86],"interpretable":[88],"probabilities.":[89],"By":[90],"including":[91],"quality":[92],"features":[93],"system,":[97],"decision":[99],"thresholds":[100],"evaluation":[103],"metrics":[104],"become":[105],"quality-dependent":[106],"consistent":[109],"across":[110],"varying":[111],"trial":[112],"conditions.":[113],"Applying":[114],"both":[115],"enhancements":[116],"on":[117,125],"ECAPA-TDNN":[119],"architecture":[120],"leads":[121],"state-of-the-art":[123],"results":[124],"all":[126],"publicly":[127],"available":[128],"VoxCeleb1":[129],"test":[130],"sets":[131],"contributed":[133],"our":[135],"winning":[136],"submissions":[137],"supervised":[140],"tracks":[142],"Vox-Celeb":[145],"Speaker":[146],"Recognition":[147],"Challenge":[148],"2020.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-10-29T00:00:00"}