{"id":"https://openalex.org/W3025075133","doi":"https://doi.org/10.21437/odyssey.2020-49","title":"Delving into VoxCeleb: Environment Invariant Speaker Recognition","display_name":"Delving into VoxCeleb: Environment Invariant Speaker Recognition","publication_year":2020,"publication_date":"2020-05-15","ids":{"openalex":"https://openalex.org/W3025075133","doi":"https://doi.org/10.21437/odyssey.2020-49","mag":"3025075133"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2020-49","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-49","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Naver Corporation, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114067866","display_name":"Jaesung Huh","orcid":"https://orcid.org/0000-0001-7247-6401"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaesung Huh","raw_affiliation_strings":["Naver Corporation, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021831317","display_name":"Seongkyu Mun","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seongkyu Mun","raw_affiliation_strings":["Naver Corporation, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038723822"],"corresponding_institution_ids":["https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":4.7597,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.95787536,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"349","last_page":"356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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":0.998199999332428,"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":0.9818000197410583,"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":0.9254000186920166,"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":0.6272051930427551},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5805092453956604},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5789253115653992},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5123423337936401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.405642569065094},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1780446469783783}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6272051930427551},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5805092453956604},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5789253115653992},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5123423337936401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.405642569065094},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1780446469783783},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/odyssey.2020-49","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-49","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1528954144","https://openalex.org/W1731081199","https://openalex.org/W1836465849","https://openalex.org/W1936725236","https://openalex.org/W1970872899","https://openalex.org/W2090716422","https://openalex.org/W2108598243","https://openalex.org/W2136879537","https://openalex.org/W2141125852","https://openalex.org/W2150769028","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2214409633","https://openalex.org/W2219249508","https://openalex.org/W2593768305","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2801581493","https://openalex.org/W2802304149","https://openalex.org/W2808631503","https://openalex.org/W2890680318","https://openalex.org/W2890964092","https://openalex.org/W2899771611","https://openalex.org/W2901368553","https://openalex.org/W2916104401","https://openalex.org/W2962788262","https://openalex.org/W2963127163","https://openalex.org/W2963173190","https://openalex.org/W2963371159","https://openalex.org/W2963450999","https://openalex.org/W2963784072","https://openalex.org/W2964154960","https://openalex.org/W2972425344","https://openalex.org/W2973190269","https://openalex.org/W2998678989","https://openalex.org/W4288091954"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2499802997","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466","https://openalex.org/W2757081366"],"abstract_inverted_index":{"Research":[0],"in":[1,30,74,100],"speaker":[2,121],"recognition":[3],"has":[4,24],"recently":[5],"seen":[6],"significant":[7,134],"progress":[8],"due":[9],"to":[10,60,110,113],"the":[11,18,41,54,62,76,95,101,108,127],"application":[12],"of":[13,20,28],"neural":[14],"network":[15,77,109],"models":[16],"and":[17,82,123],"availability":[19],"new":[21],"large-scale":[22],"datasets.There":[23],"been":[25],"a":[26],"plethora":[27],"work":[29],"search":[31],"for":[32,40],"more":[33],"powerful":[34],"architectures":[35],"or":[36],"loss":[37],"functions":[38],"suitable":[39],"task,":[42],"but":[43],"these":[44],"works":[45],"do":[46],"not":[47],"consider":[48],"what":[49],"information":[50,99],"is":[51,117],"learnt":[52],"by":[53,93],"models,":[55],"apart":[56],"from":[57],"being":[58],"able":[59],"predict":[61],"given":[63],"labels.In":[64],"this":[65,92],"work,":[66],"we":[67,132],"introduce":[68],"an":[69],"environment":[70,104],"adversarial":[71,105],"training":[72,106],"framework":[73],"which":[75,131],"can":[78],"effectively":[79],"learn":[80],"speaker-discriminative":[81],"environment-invariant":[83],"embeddings":[84],"without":[85],"explicit":[86],"domain":[87],"shift":[88],"during":[89],"training.We":[90],"achieve":[91],"utilising":[94],"previously":[96],"unused":[97],"'video'":[98],"VoxCeleb":[102,128],"dataset.The":[103],"allows":[107],"generalise":[111],"better":[112],"unseen":[114],"conditions.The":[115],"method":[116],"evaluated":[118],"on":[119,130],"both":[120],"identification":[122],"verification":[124],"tasks":[125],"using":[126],"dataset,":[129],"demonstrate":[133],"performance":[135],"improvements":[136],"over":[137],"baselines.":[138]},"counts_by_year":[{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":7}],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2025-10-10T00:00:00"}