{"id":"https://openalex.org/W4375869005","doi":"https://doi.org/10.1109/icassp49357.2023.10095702","title":"Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-to-Speech","display_name":"Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-to-Speech","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869005","doi":"https://doi.org/10.1109/icassp49357.2023.10095702"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095702","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5025983709","display_name":"Takaaki Saeki","orcid":"https://orcid.org/0000-0001-6003-768X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takaaki Saeki","raw_affiliation_strings":["Google,Japan","The University of Tokyo, Japan","Google, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,Japan","institution_ids":[]},{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Google, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heiga Zen","raw_affiliation_strings":["Google,Japan","Google, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,Japan","institution_ids":[]},{"raw_affiliation_string":"Google, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":["Google,USA","Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111040545","display_name":"Nobuyuki Morioka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobuyuki Morioka","raw_affiliation_strings":["Google,Japan","Google, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,Japan","institution_ids":[]},{"raw_affiliation_string":"Google, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025935520","display_name":"Gary Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gary Wang","raw_affiliation_strings":["Google,USA","Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092339698","display_name":"Yu Zhang","orcid":"https://orcid.org/0009-0003-3350-7609"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google,USA","Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024316712","display_name":"Ankur Bapna","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankur Bapna","raw_affiliation_strings":["Google,USA","Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024913801","display_name":"Andrew E. Rosenberg","orcid":"https://orcid.org/0000-0002-4536-8824"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["Google,USA","Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["Google,USA","Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9984999895095825,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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":0.8570438027381897},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6192686557769775},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6111326813697815},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6092188358306885},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5747509598731995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5245198011398315},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5200526118278503},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5086363554000854},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4714071750640869},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4160005748271942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8570438027381897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6192686557769775},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6111326813697815},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6092188358306885},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5747509598731995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5245198011398315},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5200526118278503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5086363554000854},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4714071750640869},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4160005748271942},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095702","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1499275966","https://openalex.org/W2025638820","https://openalex.org/W2494654097","https://openalex.org/W2938947737","https://openalex.org/W2952711665","https://openalex.org/W2964002616","https://openalex.org/W2964243274","https://openalex.org/W2972473628","https://openalex.org/W2973213036","https://openalex.org/W2998572311","https://openalex.org/W3015280134","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3095410713","https://openalex.org/W3096442195","https://openalex.org/W3097032879","https://openalex.org/W3119308075","https://openalex.org/W3161296985","https://openalex.org/W3169483174","https://openalex.org/W3181257032","https://openalex.org/W3198429080","https://openalex.org/W3205644108","https://openalex.org/W3206831804","https://openalex.org/W3209984917","https://openalex.org/W4210690962","https://openalex.org/W4221155340","https://openalex.org/W4223622550","https://openalex.org/W4226033575","https://openalex.org/W4226120743","https://openalex.org/W4296068421","https://openalex.org/W4297841232","https://openalex.org/W4313156423","https://openalex.org/W4319862218","https://openalex.org/W4319862635","https://openalex.org/W4372259881","https://openalex.org/W6696449567","https://openalex.org/W6755300632","https://openalex.org/W6762242920","https://openalex.org/W6771467084","https://openalex.org/W6772349387","https://openalex.org/W6780218876","https://openalex.org/W6782760101","https://openalex.org/W6783450753","https://openalex.org/W6798575157","https://openalex.org/W6810259195"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W2081919107","https://openalex.org/W4391272374","https://openalex.org/W2405110677","https://openalex.org/W4200068392","https://openalex.org/W2184371793","https://openalex.org/W2537969829","https://openalex.org/W4312742405"],"abstract_inverted_index":{"This":[0,57],"paper":[1],"proposes":[2],"Virtuoso,":[3],"a":[4,27,61,77],"massively":[5],"multilingual":[6,18,42,114],"speech\u2013text":[7,51,62],"joint":[8,63],"semi-supervised":[9],"learning":[10],"framework":[11,65],"for":[12,66,144],"text-to-speech":[13],"synthesis":[14],"(TTS)":[15],"models.":[16],"Existing":[17],"TTS":[19,43,78,97,115,151],"typically":[20],"supports":[21],"tens":[22],"of":[23,30,33,46,83],"languages,":[24,132],"which":[25],"are":[26,91],"small":[28],"fraction":[29],"the":[31,36],"thousands":[32],"languages":[34,47,146],"in":[35,54,130],"world.":[37],"One":[38],"difficulty":[39],"to":[40,44,71,93],"scale":[41],"hundreds":[45],"is":[48,153],"collecting":[49],"high-quality":[50,149],"paired":[52,150],"data":[53,152],"low-resource":[55],"languages.":[56],"study":[58],"extends":[59],"Maestro,":[60],"pretraining":[64],"automatic":[67],"speech":[68,72,84,104,143],"recognition":[69],"(ASR),":[70],"generation":[73],"tasks.":[74],"To":[75],"train":[76],"model":[79],"from":[80],"various":[81],"types":[82],"and":[85,98,101,105,125,133,140],"text":[86],"data,":[87],"different":[88],"training":[89],"schemes":[90],"designed":[92],"handle":[94],"supervised":[95],"(paired":[96],"ASR":[99],"data)":[100],"unsupervised":[102],"(untranscribed":[103],"unspoken":[106],"text)":[107],"datasets.":[108],"Experimental":[109],"evaluation":[110],"shows":[111],"that":[112],"1)":[113],"models":[116],"trained":[117],"on":[118],"Virtuoso":[119],"can":[120,136],"achieve":[121],"significantly":[122],"better":[123],"naturalness":[124],"intelligibility":[126],"than":[127],"baseline":[128],"ones":[129],"seen":[131],"2)":[134],"they":[135],"synthesize":[137],"reasonably":[138],"intelligible":[139],"naturally":[141],"sounding":[142],"unseen":[145],"where":[147],"no":[148],"available.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
