{"id":"https://openalex.org/W3013020904","doi":"https://doi.org/10.21437/interspeech.2020-1064","title":"In Defence of Metric Learning for Speaker Recognition","display_name":"In Defence of Metric Learning for Speaker Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3013020904","doi":"https://doi.org/10.21437/interspeech.2020-1064","mag":"3013020904"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1064","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.11982","any_repository_has_fulltext":true},"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"],"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"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449738","display_name":"Minjae Lee","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":"Minjae Lee","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112515444","display_name":"Hee-Soo Heo","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":"Hee-Soo Heo","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022555543","display_name":"Soyeon Choe","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":"Soyeon Choe","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004178515","display_name":"Chiheon Ham","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":"Chiheon Ham","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038045454","display_name":"Sunghwan Jung","orcid":"https://orcid.org/0000-0001-6552-9034"},"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":"Sunghwan Jung","raw_affiliation_strings":["Naver Corporation, South Korea"],"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"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028211638","display_name":"Icksang Han","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":"Icksang Han","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5038723822"],"corresponding_institution_ids":["https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":39.5115,"has_fulltext":false,"cited_by_count":394,"citation_normalized_percentile":{"value":0.998439,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2977","last_page":"2981"},"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":0.9986000061035156,"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":0.9970999956130981,"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/speaker-recognition","display_name":"Speaker recognition","score":0.7733979225158691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7576745748519897},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7519323229789734},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6848873496055603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5770766735076904},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5743707418441772},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5120497345924377},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4963236451148987},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4821057617664337},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4780031740665436},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05874016880989075}],"concepts":[{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7733979225158691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576745748519897},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7519323229789734},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6848873496055603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5770766735076904},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5743707418441772},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5120497345924377},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4963236451148987},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4821057617664337},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4780031740665436},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05874016880989075},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1064","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2003.11982","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.11982","pdf_url":"https://arxiv.org/pdf/2003.11982","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.11982","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.11982","pdf_url":"https://arxiv.org/pdf/2003.11982","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":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1589137271","https://openalex.org/W2117678320","https://openalex.org/W2157364932","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2502312327","https://openalex.org/W2516764878","https://openalex.org/W2601450892","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2779809129","https://openalex.org/W2794506738","https://openalex.org/W2802973008","https://openalex.org/W2808631503","https://openalex.org/W2884412522","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2938358845","https://openalex.org/W2939763029","https://openalex.org/W2951534110","https://openalex.org/W2962788625","https://openalex.org/W2962898354","https://openalex.org/W2962959915","https://openalex.org/W2963173190","https://openalex.org/W2963371159","https://openalex.org/W2963386851","https://openalex.org/W2963466847","https://openalex.org/W2963988212","https://openalex.org/W2964052309","https://openalex.org/W2969985801","https://openalex.org/W2970971581","https://openalex.org/W2972392008","https://openalex.org/W2972961496","https://openalex.org/W2972986505","https://openalex.org/W2973032144","https://openalex.org/W2981461916","https://openalex.org/W3001061282","https://openalex.org/W3003859915","https://openalex.org/W3010925296","https://openalex.org/W3015443711","https://openalex.org/W3025075133","https://openalex.org/W3099206234","https://openalex.org/W3103152812","https://openalex.org/W4287902618","https://openalex.org/W4288091954","https://openalex.org/W4289750118","https://openalex.org/W4295312788"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2160753975","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"The":[0],"objective":[1,93],"of":[2,9,59],"this":[3,52],"paper":[4],"is":[5,40],"'open-set'":[6],"speaker":[7,38,65],"recognition":[8,39,66],"unseen":[10],"speakers,":[11],"where":[12],"ideal":[13],"embeddings":[14],"should":[15],"be":[16],"able":[17],"to":[18,82],"condense":[19],"information":[20],"into":[21],"a":[22],"compact":[23],"utterance-level":[24],"representation":[25],"that":[26,41,73],"has":[27],"small":[28],"intra-speaker":[29],"and":[30,85],"large":[31],"inter-speaker":[32],"distance.":[33],"A":[34],"popular":[35,61],"belief":[36],"in":[37],"networks":[42],"trained":[43,87],"with":[44,88],"classification":[45],"objectives":[46],"outperform":[47,94],"metric":[48,91],"learning":[49,92],"methods.":[50,96],"In":[51],"paper,":[53],"we":[54],"present":[55],"an":[56],"extensive":[57],"evaluation":[58],"most":[60],"loss":[62,77],"functions":[63],"for":[64],"on":[67],"the":[68,74],"VoxCeleb":[69],"dataset.":[70],"We":[71],"demonstrate":[72],"vanilla":[75],"triplet":[76],"shows":[78],"competitive":[79],"performance":[80],"compared":[81],"classification-based":[83],"losses,":[84],"those":[86],"our":[89],"proposed":[90],"state-of-the-art":[95]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":45},{"year":2024,"cited_by_count":58},{"year":2023,"cited_by_count":80},{"year":2022,"cited_by_count":88},{"year":2021,"cited_by_count":87},{"year":2020,"cited_by_count":33}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}