{"id":"https://openalex.org/W4297841773","doi":"https://doi.org/10.21437/interspeech.2022-126","title":"Pushing the limits of raw waveform speaker recognition","display_name":"Pushing the limits of raw waveform speaker recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841773","doi":"https://doi.org/10.21437/interspeech.2022-126"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-126","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-126","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5091834525","display_name":"Jee-weon Jung","orcid":"https://orcid.org/0000-0003-0505-2988"},"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":"Jee-weon Jung","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/A5100699529","display_name":"Youjin Kim","orcid":"https://orcid.org/0009-0003-2327-0847"},"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":"Youjin Kim","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/A5070613375","display_name":"Hee-Soo Heo","orcid":"https://orcid.org/0000-0003-1567-123X"},"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":"Hee-Soo Heo","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/A5086369397","display_name":"Bong\u2010Jin Lee","orcid":"https://orcid.org/0000-0001-7896-2961"},"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":"Bong-Jin Lee","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/A5067505925","display_name":"Youngki Kwon","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":"Youngki Kwon","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/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5091834525"],"corresponding_institution_ids":["https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":8.3132,"has_fulltext":false,"cited_by_count":87,"citation_normalized_percentile":{"value":0.98330507,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2228","last_page":"2232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9239000082015991,"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":0.9239000082015991,"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/waveform","display_name":"Waveform","score":0.7584545612335205},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6775904893875122},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6466432809829712},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5096261501312256},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.23605072498321533}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7584545612335205},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6775904893875122},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6466432809829712},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5096261501312256},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.23605072498321533},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-126","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-126","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1924770834","https://openalex.org/W2037363404","https://openalex.org/W2046056978","https://openalex.org/W2150769028","https://openalex.org/W2398826216","https://openalex.org/W2502312327","https://openalex.org/W2726515241","https://openalex.org/W2802488037","https://openalex.org/W2808631503","https://openalex.org/W2889151164","https://openalex.org/W2890964092","https://openalex.org/W2928165649","https://openalex.org/W2947256846","https://openalex.org/W2963263347","https://openalex.org/W2964052309","https://openalex.org/W2969985801","https://openalex.org/W2972909277","https://openalex.org/W2981952041","https://openalex.org/W3004940340","https://openalex.org/W3005680577","https://openalex.org/W3010893827","https://openalex.org/W3024869864","https://openalex.org/W3035452548","https://openalex.org/W3035524453","https://openalex.org/W3036601975","https://openalex.org/W3044308976","https://openalex.org/W3094735979","https://openalex.org/W3159481202","https://openalex.org/W3161606033","https://openalex.org/W3163187953","https://openalex.org/W3167533889","https://openalex.org/W3170863103","https://openalex.org/W4221145109","https://openalex.org/W4221161750","https://openalex.org/W4224916701","https://openalex.org/W4283030875","https://openalex.org/W4285580150","https://openalex.org/W4287633917","https://openalex.org/W4287635082","https://openalex.org/W4287931183","https://openalex.org/W4309845474","https://openalex.org/W4313156423","https://openalex.org/W4394647302"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W2611678594","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149"],"abstract_inverted_index":{"In":[0],"recent":[1,56],"years,":[2],"speaker":[3,46,62],"recognition":[4,47],"systems":[5,19],"based":[6,49,89,98],"on":[7,36,50,90,99],"raw":[8,51,100],"waveform":[9,52,101],"inputs":[10,102],"have":[11,148],"received":[12],"increasing":[13],"attention.However,":[14],"the":[15,24,37,65,86,95,109,112,116,142],"performance":[16],"of":[17,80,111,118,132,152,161],"such":[18],"are":[20],"typically":[21],"inferior":[22],"to":[23],"state-of-the-art":[25,87],"handcrafted":[26,91],"feature-based":[27],"counterparts,":[28],"which":[29,82],"demonstrate":[30],"equal":[31,77],"error":[32,78],"rates":[33],"under":[34],"1%":[35],"popular":[38],"VoxCeleb1":[39],"test":[40],"set.This":[41],"paper":[42],"proposes":[43],"a":[44,104,149,158],"novel":[45],"model":[48,54,74,97,114,123],"inputs.The":[53],"incorporates":[55],"advances":[57],"in":[58,115,129],"machine":[59],"learning":[60,120],"and":[61,69,93],"verification,":[63],"including":[64],"Res2Net":[66],"backbone":[67],"module":[68],"multi-layer":[70],"feature":[71],"aggregation.Our":[72],"best":[73,96],"achieves":[75],"an":[76],"rate":[79],"0.89%,":[81],"is":[83,139],"competitive":[84],"with":[85,157],"models":[88],"features,":[92],"outperforms":[94,124],"by":[103],"large":[105],"margin.We":[106],"also":[107],"explore":[108],"application":[110],"proposed":[113],"context":[117],"self-supervised":[119,122,137],"framework.Our":[121],"single":[125],"phase-based":[126],"existing":[127],"works":[128],"this":[130],"line":[131],"research.Finally,":[133],"we":[134,146],"show":[135],"that":[136],"pre-training":[138],"effective":[140],"for":[141],"semi-supervised":[143],"scenario":[144],"where":[145],"only":[147],"small":[150],"set":[151,160],"labelled":[153],"training":[154],"data,":[155],"along":[156],"larger":[159],"unlabelled":[162],"examples.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-13T08:25:38.343686","created_date":"2025-10-10T00:00:00"}