{"id":"https://openalex.org/W4406461681","doi":"https://doi.org/10.1109/slt61566.2024.10832365","title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset For Large-Scale Speech Generation","display_name":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset For Large-Scale Speech Generation","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461681","doi":"https://doi.org/10.1109/slt61566.2024.10832365"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5033905098","display_name":"Haorui He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haorui He","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085101543","display_name":"Zengqiang Shang","orcid":"https://orcid.org/0000-0002-9225-2138"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengqiang Shang","raw_affiliation_strings":["Institute of Acoustics CAS,Laboratory of Speech &#x0026; Intelligent Information Processing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics CAS,Laboratory of Speech &#x0026; Intelligent Information Processing,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005342759","display_name":"Chaoren Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoren Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050989901","display_name":"Xuyuan Li","orcid":"https://orcid.org/0000-0003-0533-3552"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuyuan Li","raw_affiliation_strings":["Institute of Acoustics CAS,Laboratory of Speech &#x0026; Intelligent Information Processing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics CAS,Laboratory of Speech &#x0026; Intelligent Information Processing,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102714342","display_name":"Yicheng Gu","orcid":"https://orcid.org/0000-0002-0506-3364"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yicheng Gu","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103185155","display_name":"Hua Hua","orcid":"https://orcid.org/0000-0003-4942-5395"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Hua","raw_affiliation_strings":["Institute of Acoustics CAS,Laboratory of Speech &#x0026; Intelligent Information Processing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics CAS,Laboratory of Speech &#x0026; Intelligent Information Processing,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050952833","display_name":"Liwei Liu","orcid":"https://orcid.org/0000-0002-0578-1091"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liwei Liu","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100759899","display_name":"Chen Yang","orcid":"https://orcid.org/0000-0001-8545-9379"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Yang","raw_affiliation_strings":["Institute of Acoustics CAS,Laboratory of Speech &#x0026; Intelligent Information Processing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics CAS,Laboratory of Speech &#x0026; Intelligent Information Processing,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325927","display_name":"Jiaqi Li","orcid":"https://orcid.org/0000-0001-8010-9636"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038456140","display_name":"Peiyang Shi","orcid":"https://orcid.org/0000-0002-0496-171X"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiyang Shi","raw_affiliation_strings":["Institute of Acoustics CAS,Laboratory of Speech &#x0026; Intelligent Information Processing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics CAS,Laboratory of Speech &#x0026; Intelligent Information Processing,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090055283","display_name":"Yuancheng Wang","orcid":"https://orcid.org/0000-0002-6253-8311"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuancheng Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048500768","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0002-3930-8294"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Shanghai AI Laboratory,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,Shanghai,China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036446253","display_name":"Pengyuan Zhang","orcid":"https://orcid.org/0000-0001-6838-5160"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyuan Zhang","raw_affiliation_strings":["Institute of Acoustics CAS,Laboratory of Speech &#x0026; Intelligent Information Processing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics CAS,Laboratory of Speech &#x0026; Intelligent Information Processing,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhizheng Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5033905098"],"corresponding_institution_ids":["https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":12.0828,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.98892879,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"885","last_page":"890"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980000257492065,"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/T12031","display_name":"Speech and dialogue systems","score":0.9969000220298767,"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":0.7854771614074707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6164617538452148},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5477882027626038},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5131016969680786},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4497685730457306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4383352994918823},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0428636372089386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7854771614074707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6164617538452148},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5477882027626038},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5131016969680786},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4497685730457306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4383352994918823},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0428636372089386},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"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":24,"referenced_works":["https://openalex.org/W2970641574","https://openalex.org/W2972359262","https://openalex.org/W2995181338","https://openalex.org/W2998572311","https://openalex.org/W3095410713","https://openalex.org/W3143523927","https://openalex.org/W3198533616","https://openalex.org/W3198694222","https://openalex.org/W3209984917","https://openalex.org/W4225302959","https://openalex.org/W4252812408","https://openalex.org/W4377010126","https://openalex.org/W4381786045","https://openalex.org/W4385822293","https://openalex.org/W4385822353","https://openalex.org/W4392903247","https://openalex.org/W4392909842","https://openalex.org/W4402111455","https://openalex.org/W4406461271","https://openalex.org/W6772349387","https://openalex.org/W6796730497","https://openalex.org/W6853188576","https://openalex.org/W6862144568","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2216757598","https://openalex.org/W234770729","https://openalex.org/W4387496629","https://openalex.org/W3013209356","https://openalex.org/W2489800615","https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2],"speech":[3,22,35,48,58,75,98,105],"generation":[4,49],"models":[5],"have":[6],"been":[7],"significantly":[8],"driven":[9],"by":[10],"the":[11,28,42,79,87,110],"use":[12],"of":[13,30,57,66,81,112],"large-scale":[14],"training":[15,102],"data.":[16],"However,":[17],"producing":[18],"highly":[19],"spontaneous,":[20],"human-like":[21],"remains":[23],"a":[24,63],"challenge":[25],"due":[26],"to":[27,69,93],"scarcity":[29],"large,":[31],"diverse,":[32],"and":[33,46,73,115],"spontaneous":[34,74],"datasets.":[36],"In":[37],"response,":[38],"we":[39,83],"introduce":[40],"Emilia,":[41,82],"first":[43,88],"large-scale,":[44],"multilingual,":[45],"diverse":[47],"dataset.":[50],"Emilia":[51,114],"starts":[52],"with":[53,104],"over":[54],"101k":[55],"hours":[56],"across":[59],"six":[60],"languages,":[61],"covering":[62],"wide":[64],"range":[65],"speaking":[67],"styles":[68],"enable":[70],"more":[71],"natural":[72],"generation.":[76],"To":[77],"facilitate":[78],"scale-up":[80],"also":[84],"present":[85],"Emilia-Pipe,":[86],"open-source":[89],"preprocessing":[90],"pipeline":[91],"designed":[92],"efficiently":[94],"transform":[95],"raw,":[96],"in-the-wild":[97],"data":[99,103],"into":[100],"high-quality":[101],"annotations.":[106],"Experimental":[107],"results":[108],"demonstrate":[109],"effectiveness":[111],"both":[113],"Emilia-Pipe.":[116],"Demos":[117],"are":[118],"available":[119],"at:":[120],"https://emilia-dataset.github.io/Emilia-Demo-Page/.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":21},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
