{"id":"https://openalex.org/W3015598461","doi":"https://doi.org/10.1109/icassp40776.2020.9054017","title":"CN-Celeb: A Challenging Chinese Speaker Recognition Dataset","display_name":"CN-Celeb: A Challenging Chinese Speaker Recognition Dataset","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015598461","doi":"https://doi.org/10.1109/icassp40776.2020.9054017","mag":"3015598461"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5103194601","display_name":"Yue Fan","orcid":"https://orcid.org/0000-0001-6670-2011"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Y. Fan","raw_affiliation_strings":["Nanjing University of Science and Technology,Key Laboratory of Transient Physics,China","Key Laboratory of Transient Physics, Nanjing University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,Key Laboratory of Transient Physics,China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"Key Laboratory of Transient Physics, Nanjing University of Science and Technology, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049139590","display_name":"Jian Kang","orcid":"https://orcid.org/0000-0003-3797-256X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"J.W. Kang","raw_affiliation_strings":["Tsinghua University,Center for Speech and Language Technologies,China","Center for Speech and Language Technologies, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066028874","display_name":"L.T. Li","orcid":"https://orcid.org/0000-0002-9014-5005"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"L.T. Li","raw_affiliation_strings":["Tsinghua University,Center for Speech and Language Technologies,China","Center for Speech and Language Technologies, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057072477","display_name":"Kunlun Li","orcid":"https://orcid.org/0000-0002-0417-744X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"K.C. Li","raw_affiliation_strings":["Tsinghua University,Center for Speech and Language Technologies,China","Center for Speech and Language Technologies, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088434188","display_name":"Hanrui Chen","orcid":"https://orcid.org/0009-0009-4072-0153"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"H.L. Chen","raw_affiliation_strings":["Tsinghua University,Center for Speech and Language Technologies,China","Center for Speech and Language Technologies, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057433359","display_name":"Sang Cheng","orcid":"https://orcid.org/0000-0001-5592-1382"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"S.T. Cheng","raw_affiliation_strings":["Tsinghua University,Center for Speech and Language Technologies,China","Center for Speech and Language Technologies, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037574665","display_name":"P.Y. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"P.Y. Zhang","raw_affiliation_strings":["Tsinghua University,Center for Speech and Language Technologies,China","Center for Speech and Language Technologies, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012699980","display_name":"Zhengxu Zhou","orcid":"https://orcid.org/0000-0001-6064-7568"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Z.Y. Zhou","raw_affiliation_strings":["Tsinghua University,Center for Speech and Language Technologies,China","Center for Speech and Language Technologies, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036994482","display_name":"Yunqi Cai","orcid":"https://orcid.org/0000-0002-5635-1956"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Y.Q. Cai","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,China","Department of Computer Science and Technology, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055391415","display_name":"Deguang Wang","orcid":"https://orcid.org/0009-0005-3970-7630"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"D. Wang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology,China","Beijing National Research Center for Information Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology,China","institution_ids":["https://openalex.org/I4210156423"]},{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, China","institution_ids":["https://openalex.org/I4210156423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5103194601"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":14.3488,"has_fulltext":false,"cited_by_count":176,"citation_normalized_percentile":{"value":0.99136143,"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":"7604","last_page":"7608"},"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.7664343118667603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7526329755783081},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6593700051307678},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.574130117893219},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5183438062667847},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5128839015960693},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49785876274108887},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4844915568828583},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4530763328075409},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.41495025157928467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36764979362487793},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34541743993759155},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07799762487411499}],"concepts":[{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7664343118667603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7526329755783081},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6593700051307678},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.574130117893219},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5183438062667847},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5128839015960693},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49785876274108887},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4844915568828583},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4530763328075409},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.41495025157928467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36764979362487793},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34541743993759155},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07799762487411499},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W86526702","https://openalex.org/W1524333225","https://openalex.org/W1589137271","https://openalex.org/W1686810756","https://openalex.org/W1964846093","https://openalex.org/W2107638917","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2166637769","https://openalex.org/W2184045248","https://openalex.org/W2194775991","https://openalex.org/W2404617565","https://openalex.org/W2516764878","https://openalex.org/W2604341542","https://openalex.org/W2604379605","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2943235166","https://openalex.org/W2962832278","https://openalex.org/W2969985801","https://openalex.org/W6603481629","https://openalex.org/W6631362777","https://openalex.org/W6635152626","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6735927292","https://openalex.org/W6737563559","https://openalex.org/W6740167877","https://openalex.org/W6761937618"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Recently,":[0],"researchers":[1,153],"set":[2],"an":[3],"ambitious":[4],"goal":[5],"of":[6,55,137],"conducting":[7],"speaker":[8,58,70,101,125],"recognition":[9,59,71,102,126],"in":[10,60,93,132],"unconstrained":[11,61],"conditions":[12],"where":[13],"the":[14,53,75,109,117,135],"variations":[15],"on":[16,57,111,120],"ambient,":[17],"channel":[18,40],"and":[19,38,49,88,105,154],"emotion":[20],"could":[21],"be":[22,141,156],"arbitrary.":[23],"However,":[24],"most":[25],"publicly":[26],"available":[27],"datasets":[28,43],"are":[29],"collected":[30,73],"under":[31],"constrained":[32],"environments,":[33],"i.e.,":[34],"with":[35,98],"little":[36],"noise":[37],"limited":[39],"variation.":[41],"These":[42],"tend":[44],"to":[45,116],"deliver":[46],"over-optimistic":[47],"performance":[48,110,136],"do":[50],"not":[51],"meet":[52],"request":[54],"research":[56],"conditions.In":[62],"this":[63],"paper,":[64],"we":[65],"present":[66],"CN-Celeb,":[67],"a":[68,122],"large-scale":[69],"dataset":[72,78],"\u2018in":[74],"wild\u2019.":[76],"This":[77,128],"contains":[79],"more":[80],"than":[81,144],"130,000":[82],"utterances":[83],"from":[84,158],"1,000":[85],"Chinese":[86],"celebrities,":[87],"covers":[89],"11":[90],"different":[91],"genres":[92],"real":[94],"world.":[95],"Experiments":[96],"conducted":[97],"two":[99],"state-of-the-art":[100],"approaches":[103],"(i-vector":[104],"x-vector)":[106],"show":[107],"that":[108,131],"CN-Celeb":[112],"is":[113,150],"far":[114],"inferior":[115],"one":[118],"obtained":[119],"Vox-Celeb,":[121],"widely":[123],"used":[124],"dataset.":[127],"result":[129],"demonstrates":[130],"real-life":[133],"conditions,":[134],"existing":[138],"techniques":[139],"might":[140],"much":[142],"worse":[143],"it":[145],"was":[146],"thought.":[147],"Our":[148],"database":[149],"free":[151],"for":[152],"can":[155],"downloaded":[157],"http://project.cslt.org.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":39},{"year":2022,"cited_by_count":38},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":10}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}
