{"id":"https://openalex.org/W7133246731","doi":"https://doi.org/10.52202/075280-0618","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","display_name":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W7133246731","doi":"https://doi.org/10.52202/075280-0618"},"language":"en","primary_location":{"id":"doi:10.52202/075280-0618","doi":"https://doi.org/10.52202/075280-0618","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-0618","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.15687","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063364645","display_name":"Matthew Le","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthew Le","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108691882","display_name":"Apoorv Vyas","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Apoorv Vyas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127817985","display_name":"Bowen Shi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bowen Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038907218","display_name":"Brian Karrer","orcid":"https://orcid.org/0000-0002-6252-8332","observed_orcids":["https://orcid.org/0000-0002-6252-8332"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Karrer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003052411","display_name":"Leda Sar\u0131","orcid":"https://orcid.org/0000-0002-3754-1156","observed_orcids":["https://orcid.org/0000-0002-3754-1156"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leda Sari","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083546712","display_name":"Rashel Moritz","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rashel Moritz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130138813","display_name":"Mary Williamson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mary Williamson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028956985","display_name":"Vimal Manohar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vimal Manohar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005191803","display_name":"Yossi Adi","orcid":"https://orcid.org/0000-0003-2237-3898","observed_orcids":["https://orcid.org/0000-0003-2237-3898"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yossi Adi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074237839","display_name":"Jay Mahadeokar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jay Mahadeokar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217","observed_orcids":["https://orcid.org/0000-0001-5546-5217"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Ning Hsu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.3812,"has_fulltext":true,"cited_by_count":171,"citation_normalized_percentile":{"value":0.99566729,"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":"14005","last_page":"14034"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/text-to-speech","display_name":"text-to-speech","score":0.8999999761581421},{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.7139999866485596},{"id":"https://openalex.org/keywords/non-autoregressive-models","display_name":"non-autoregressive models","score":0.9039999842643738},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.7360000014305115},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"noise reduction","score":0.7450000047683716},{"id":"https://openalex.org/keywords/content-editing","display_name":"content editing","score":0.6990000009536743},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.5220000147819519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6133999824523926},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5044999718666077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44179999828338623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4343999922275543},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39500001072883606},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2994000017642975},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/075280-0618","doi":"https://doi.org/10.52202/075280-0618","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-0618","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2306.15687","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.15687","pdf_url":"https://arxiv.org/pdf/2306.15687","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2306.15687","doi":"https://doi.org/10.48550/arxiv.2306.15687","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2306.15687","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.15687","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.15687","pdf_url":"https://arxiv.org/pdf/2306.15687","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7133246731.pdf","grobid_xml":"https://content.openalex.org/works/W7133246731.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2893749619","https://openalex.org/W2972359262","https://openalex.org/W3097777922","https://openalex.org/W4288099666","https://openalex.org/W4366460484","https://openalex.org/W4386076005"],"related_works":["https://openalex.org/W4390306858","https://openalex.org/W4379924545","https://openalex.org/W4415337135","https://openalex.org/W4391271997","https://openalex.org/W4410852835","https://openalex.org/W4416549788","https://openalex.org/W7221975209","https://openalex.org/W4366460484","https://openalex.org/W7141059517","https://openalex.org/W4392904511"],"abstract_inverted_index":{"Large-scale":[0],"generative":[1,35,57],"models":[2,14,36],"such":[3],"as":[4,107],"GPT":[5],"and":[6,44,76,132,155],"DALL-E":[7],"have":[8],"revolutionized":[9],"the":[10,53,140],"research":[11],"community.":[12],"These":[13],"not":[15,29,87],"only":[16],"generate":[17],"high":[18],"fidelity":[19],"outputs,":[20],"but":[21,103],"are":[22,37,86],"also":[23,110],"generalists":[24],"which":[25],"can":[26,95,109,116,170],"solve":[27],"tasks":[28,99],"explicitly":[30],"taught.":[31],"In":[32,47,136],"contrast,":[33],"speech":[34,60,84],"still":[38],"primitive":[39],"in":[40,173],"terms":[41],"of":[42,83],"scale":[43],"task":[45],"generalization.":[46],"this":[48],"paper,":[49],"we":[50],"present":[51],"Voicebox,":[52],"most":[54],"versatile":[55],"text-guided":[56],"model":[58,68,144],"for":[59,119],"at":[61],"scale.":[62],"Voicebox":[63,94,115,138],"is":[64,104],"a":[65],"non-autoregressive":[66],"flow-matching":[67],"trained":[69,78],"to":[70,92,164],"infill":[71],"speech,":[72],"given":[73],"audio":[74,156],"context":[75],"text,":[77],"on":[79,112,146],"over":[80],"50K":[81],"hours":[82],"that":[85],"filtered":[88],"or":[89,121],"enhanced.":[90],"Similar":[91],"GPT,":[93],"perform":[96],"many":[97],"different":[98],"through":[100],"in-context":[101],"learning,":[102],"more":[105],"flexible":[106],"it":[108],"condition":[111],"future":[113],"context.":[114],"be":[117,171],"used":[118],"mono":[120],"cross-lingual":[122],"zero-shot":[123,142],"text-to-speech":[124],"synthesis,":[125],"noise":[126],"removal,":[127],"content":[128],"editing,":[129],"style":[130],"conversion,":[131],"diverse":[133],"sample":[134],"generation.":[135],"particular,":[137],"outperforms":[139],"state-of-the-art":[141],"TTS":[143],"VALL-E":[145],"both":[147],"intelligibility":[148],"(5.9%":[149],"vs":[150,159],"1.9%":[151],"word":[152],"error":[153],"rates)":[154],"similarity":[157],"(0.580":[158],"0.681)":[160],"while":[161],"being":[162],"up":[163],"20":[165],"times":[166],"faster.":[167],"Audio":[168],"samples":[169],"found":[172],"\\url{https://voicebox.metademolab.com}.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":51},{"year":2025,"cited_by_count":39},{"year":2024,"cited_by_count":64},{"year":2023,"cited_by_count":17}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-03-03T00:00:00"}