{"id":"https://openalex.org/W3198275944","doi":"https://doi.org/10.21437/interspeech.2021-1280","title":"Exploring wav2vec 2.0 on Speaker Verification and Language Identification","display_name":"Exploring wav2vec 2.0 on Speaker Verification and Language Identification","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198275944","doi":"https://doi.org/10.21437/interspeech.2021-1280","mag":"3198275944"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1280","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5027251228","display_name":"Zhiyun Fan","orcid":"https://orcid.org/0000-0001-9180-7392"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyun Fan","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457571","display_name":"Meng Li","orcid":"https://orcid.org/0000-0003-3553-0813"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Li","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101400153","display_name":"Shiyu Zhou","orcid":"https://orcid.org/0000-0002-6889-0316"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyu Zhou","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","Institute of Automation, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027251228"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210100255","https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":15.3997,"has_fulltext":false,"cited_by_count":141,"citation_normalized_percentile":{"value":0.99247058,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1509","last_page":"1513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9929999709129333,"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/T11309","display_name":"Music and Audio Processing","score":0.9872999787330627,"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":0.7371742129325867},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6873507499694824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4976241886615753},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.43064653873443604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42032772302627563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37787219882011414},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3272686302661896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7371742129325867},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6873507499694824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4976241886615753},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.43064653873443604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42032772302627563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37787219882011414},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3272686302661896},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1280","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2187089797","https://openalex.org/W2462831000","https://openalex.org/W2726515241","https://openalex.org/W2794506738","https://openalex.org/W2797569913","https://openalex.org/W2896457183","https://openalex.org/W2900028034","https://openalex.org/W2916104401","https://openalex.org/W2936078256","https://openalex.org/W2936791331","https://openalex.org/W2944828972","https://openalex.org/W2948012107","https://openalex.org/W2962739339","https://openalex.org/W2963371159","https://openalex.org/W2971840980","https://openalex.org/W2972808922","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2981087920","https://openalex.org/W2981991061","https://openalex.org/W3010814938","https://openalex.org/W3015213852","https://openalex.org/W3036601975","https://openalex.org/W3103152812","https://openalex.org/W4297808394","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2126085626","https://openalex.org/W2002345321","https://openalex.org/W208363076","https://openalex.org/W1843883989","https://openalex.org/W2087341511","https://openalex.org/W2249138175","https://openalex.org/W4230495983","https://openalex.org/W1521049138","https://openalex.org/W2954943288","https://openalex.org/W2070360960"],"abstract_inverted_index":{"Wav2vec":[0],"2.0":[1,56,72],"is":[2],"a":[3,13,82],"recently":[4],"proposed":[5],"self-supervised":[6,39],"framework":[7,40],"for":[8,135],"speech":[9,25],"representation":[10],"learning.It":[11],"follows":[12],"two-stage":[14],"training":[15],"process":[16],"of":[17,70,90,102,112,118],"pre-training":[18],"and":[19,21,44,64,109],"fine-tuning,":[20],"performs":[22],"well":[23],"in":[24],"recognition":[26],"tasks":[27,76],"especially":[28],"ultra-low":[29],"resource":[30],"cases.In":[31],"this":[32],"work,":[33],"we":[34,47,66,80,98,122],"attempt":[35],"to":[36,41,52,126],"extend":[37],"the":[38,59,62,68,74,93,105,115,119,128,132,136],"speaker":[42,63,78],"verification":[43],"language":[45,96],"identification.First,":[46],"use":[48],"some":[49],"preliminary":[50],"experiments":[51],"indicate":[53],"that":[54],"wav2vec":[55,71],"can":[57],"capture":[58],"information":[60],"about":[61],"language.Then":[65],"demonstrate":[67],"effectiveness":[69],"on":[73,92,104,114],"two":[75,137],"respectively.For":[77],"verification,":[79],"obtain":[81,99],"new":[83],"state-of-the-art":[84],"result,":[85],"Equal":[86],"Error":[87],"Rate":[88],"(EER)":[89],"3.61%":[91],"VoxCeleb1":[94],"dataset.For":[95],"identification,":[97],"an":[100,110],"EER":[101,111],"12.02%":[103],"1":[106],"second":[107],"condition":[108,117],"3.47%":[113],"full-length":[116],"AP17-OLR":[120],"dataset.Finally,":[121],"utilize":[123],"one":[124],"model":[125],"achieve":[127],"unified":[129],"modeling":[130],"by":[131],"multi-task":[133],"learning":[134],"tasks.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":51},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":6}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}