{"id":"https://openalex.org/W2995929068","doi":"https://doi.org/10.48550/arxiv.1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","display_name":"Common Voice: A Massively-Multilingual Speech Corpus","publication_year":2019,"publication_date":"2019-12-13","ids":{"openalex":"https://openalex.org/W2995929068","doi":"https://doi.org/10.48550/arxiv.1912.06670","mag":"2995929068"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1912.06670","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.06670","pdf_url":"https://arxiv.org/pdf/1912.06670","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1912.06670","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066459127","display_name":"Rosana Ardila","orcid":"https://orcid.org/0000-0003-0042-3778","observed_orcids":["https://orcid.org/0000-0003-0042-3778"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ardila, Rosana","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000451468","display_name":"Megan Branson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Branson, Megan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109296601","display_name":"Kelly Davis","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Davis, Kelly","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042712973","display_name":"Michael Henretty","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Henretty, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028420890","display_name":"Michael K\u00f6hler","orcid":"https://orcid.org/0000-0002-8372-9811","observed_orcids":["https://orcid.org/0000-0002-8372-9811"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kohler, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088964009","display_name":"Josh Meyer","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meyer, Josh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087146323","display_name":"Reuben Morais","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Morais, Reuben","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091726883","display_name":"Lindsay Saunders","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saunders, Lindsay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076604380","display_name":"Francis Morton Tyers","orcid":"https://orcid.org/0000-0001-6108-2220","observed_orcids":["https://orcid.org/0000-0001-6108-2220"]},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tyers, Francis M.","raw_affiliation_strings":["Indiana University, Bloomington, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, United States","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":null,"display_name":"Weber, Gregor","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weber, Gregor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":905,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.0,"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":0.0,"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/common-voice","display_name":"Common Voice","score":0.9139999747276306},{"id":"https://openalex.org/keywords/multilingual-speech-corpus","display_name":"multilingual speech corpus","score":0.8579999804496765},{"id":"https://openalex.org/keywords/transcribed-speech","display_name":"transcribed speech","score":0.8159999847412109},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.8740000128746033},{"id":"https://openalex.org/keywords/crowdsourced-data-collection","display_name":"crowdsourced data collection","score":0.7080000042915344},{"id":"https://openalex.org/keywords/language-identification","display_name":"language identification","score":0.8539999723434448},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.8640000224113464},{"id":"https://openalex.org/keywords/deepspeech","display_name":"DeepSpeech","score":0.8399999737739563},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.7680000066757202},{"id":"https://openalex.org/keywords/character-error-rate","display_name":"character error rate","score":0.7950000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7987213134765625},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.653984546661377},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.5716615319252014},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.547267735004425},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5331992506980896},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5270612239837646},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.505509614944458},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.46870583295822144},{"id":"https://openalex.org/C2780769345","wikidata":"https://www.wikidata.org/wiki/Q9309","display_name":"Welsh","level":2,"score":0.46026450395584106},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4141373932361603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3969990313053131},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2722013592720032},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22675821185112},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1547941267490387},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1912.06670","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.06670","pdf_url":"https://arxiv.org/pdf/1912.06670","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"mag:2995929068","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1912.06670.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1912.06670","doi":"https://doi.org/10.48550/arxiv.1912.06670","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1912.06670","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1912.06670","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.06670","pdf_url":"https://arxiv.org/pdf/1912.06670","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1922655562","https://openalex.org/W2127141656","https://openalex.org/W2292087804","https://openalex.org/W2757672955","https://openalex.org/W3084713055"],"related_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W3030437843","https://openalex.org/W2963403868","https://openalex.org/W3099782249","https://openalex.org/W2936774411","https://openalex.org/W2996383576","https://openalex.org/W2962760690","https://openalex.org/W2726515241","https://openalex.org/W2995181338","https://openalex.org/W2963341956","https://openalex.org/W2842511635","https://openalex.org/W2963765325","https://openalex.org/W3029923669","https://openalex.org/W2938835250","https://openalex.org/W3037057938","https://openalex.org/W2327501763","https://openalex.org/W1524333225","https://openalex.org/W3010812523","https://openalex.org/W2094721231"],"abstract_inverted_index":{"The":[0,55],"Common":[1,18,43,123],"Voice":[2,19,44],"corpus":[3,98],"is":[4,20,94],"a":[5,69,140],"massively-multilingual":[6],"collection":[7,51],"of":[8,64,71,87,109,111,115,152,175],"transcribed":[9],"speech":[10,13,104,127],"intended":[11],"for":[12,22,48,103,122,156],"technology":[14],"research":[15],"and":[16,40,52,62,113,171],"development.":[17],"designed":[21],"Automatic":[23,187],"Speech":[24,188],"Recognition":[25],"purposes":[26],"but":[27],"can":[28],"be":[29],"useful":[30],"in":[31,84,99,107],"other":[32],"domains":[33],"(e.g.":[34],"language":[35],"identification).":[36],"To":[37,90],"achieve":[38],"scale":[39],"sustainability,":[41],"the":[42,95,100,180],"project":[45],"employs":[46],"crowdsourcing":[47],"both":[49,106],"data":[50,53],"validation.":[54],"most":[56,174],"recent":[57],"release":[58],"includes":[59],"29":[60],"languages,":[61,177],"as":[63],"November":[65],"2019":[66],"there":[67],"are":[68,179],"total":[70],"38":[72],"languages":[73,159],"collecting":[74],"data.":[75],"Over":[76],"50,000":[77],"individuals":[78],"have":[79],"participated":[80],"so":[81],"far,":[82],"resulting":[83],"2,500":[85],"hours":[86,112],"collected":[88],"audio.":[89],"our":[91],"knowledge":[92],"this":[93],"largest":[96],"audio":[97],"public":[101],"domain":[102],"recognition,":[105],"terms":[108],"number":[110,114],"languages.":[116],"As":[117],"an":[118,146],"example":[119],"use":[120],"case":[121],"Voice,":[124],"we":[125,144],"present":[126],"recognition":[128],"experiments":[129],"using":[130],"Mozilla's":[131],"DeepSpeech":[132],"Speech-to-Text":[133],"toolkit.":[134],"By":[135],"applying":[136],"transfer":[137],"learning":[138],"from":[139],"source":[141],"English":[142],"model,":[143],"find":[145],"average":[147],"Character":[148],"Error":[149],"Rate":[150],"improvement":[151],"5.99":[153],"+/-":[154],"5.48":[155],"twelve":[157],"target":[158],"(German,":[160],"French,":[161],"Italian,":[162],"Turkish,":[163],"Catalan,":[164],"Slovenian,":[165],"Welsh,":[166],"Irish,":[167],"Breton,":[168],"Tatar,":[169],"Chuvash,":[170],"Kabyle).":[172],"For":[173],"these":[176,178],"first":[181],"ever":[182],"published":[183],"results":[184],"on":[185],"end-to-end":[186],"Recognition.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":136},{"year":2024,"cited_by_count":201},{"year":2023,"cited_by_count":232},{"year":2022,"cited_by_count":151},{"year":2021,"cited_by_count":137},{"year":2020,"cited_by_count":40},{"year":2018,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}