{"id":"https://openalex.org/W4392903365","doi":"https://doi.org/10.1109/icassp48485.2024.10448074","title":"Extending Multilingual Speech Synthesis to 100+ Languages without Transcribed Data","display_name":"Extending Multilingual Speech Synthesis to 100+ Languages without Transcribed Data","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903365","doi":"https://doi.org/10.1109/icassp48485.2024.10448074"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/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"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Takaaki Saeki","raw_affiliation_strings":["Google,USA","The University of Tokyo, Japan","Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"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/A5111040545","display_name":"Nobuyuki Morioka","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":"Nobuyuki Morioka","raw_affiliation_strings":["Google DeepMind,Japan","Google DeepMind, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,Japan","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google DeepMind, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063926383","display_name":"Isaac Elias","orcid":"https://orcid.org/0000-0001-9035-5419"},"institutions":[{"id":"https://openalex.org/I4210117425","display_name":"Google (Israel)","ror":"https://ror.org/02c20ys54","country_code":"IL","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210117425","https://openalex.org/I4210128969"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Isaac Elias","raw_affiliation_strings":["Google,Israel","Google, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,Israel","institution_ids":["https://openalex.org/I4210117425"]},{"raw_affiliation_string":"Google, Israel","institution_ids":["https://openalex.org/I4210117425"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037751863","display_name":"Kyle Kastner","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":"Kyle Kastner","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/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390"},"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":"middle","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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"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":"Heiga Zen","raw_affiliation_strings":["Google DeepMind,Japan","Google DeepMind, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,Japan","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google DeepMind, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110711540","display_name":"Fran\u00e7oise Beaufays","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":"Fran\u00e7oise Beaufays","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/A5035607064","display_name":"Hadar Shemtov","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":"Hadar Shemtov","raw_affiliation_strings":["Google DeepMind,USA","Google DeepMind, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google DeepMind, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11546","last_page":"11550"},"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/T10860","display_name":"Speech 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/T11309","display_name":"Music 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/computer-science","display_name":"Computer science","score":0.836544930934906},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7486652135848999},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7293277978897095},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6170850396156311},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6091516017913818},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6088255047798157},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5935248136520386},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5914478898048401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5208926200866699}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.836544930934906},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7486652135848999},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7293277978897095},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6170850396156311},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6091516017913818},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6088255047798157},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5935248136520386},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5914478898048401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5208926200866699},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/icassp48485.2024.10448074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2025638820","https://openalex.org/W2494654097","https://openalex.org/W2889028433","https://openalex.org/W2952468927","https://openalex.org/W2962699523","https://openalex.org/W2970854433","https://openalex.org/W3035390927","https://openalex.org/W3036601975","https://openalex.org/W3095410713","https://openalex.org/W3096303254","https://openalex.org/W3097777922","https://openalex.org/W3119308075","https://openalex.org/W3161296985","https://openalex.org/W3169483174","https://openalex.org/W3181257032","https://openalex.org/W3197294703","https://openalex.org/W4221155340","https://openalex.org/W4226033575","https://openalex.org/W4226120743","https://openalex.org/W4285189120","https://openalex.org/W4288099666","https://openalex.org/W4297841354","https://openalex.org/W4297841605","https://openalex.org/W4297841714","https://openalex.org/W4313679638","https://openalex.org/W4319862218","https://openalex.org/W4319862245","https://openalex.org/W4319862635","https://openalex.org/W4323066695","https://openalex.org/W4372259881","https://openalex.org/W4375869005","https://openalex.org/W4378105483","https://openalex.org/W4382202703","https://openalex.org/W4385764360","https://openalex.org/W4390075359","https://openalex.org/W6696449567","https://openalex.org/W6755207826","https://openalex.org/W6762242920","https://openalex.org/W6762521896","https://openalex.org/W6780218876","https://openalex.org/W6784642771","https://openalex.org/W6798575157","https://openalex.org/W6810259195","https://openalex.org/W6810673746","https://openalex.org/W6838929754","https://openalex.org/W6840815571","https://openalex.org/W6846618694","https://openalex.org/W6848735303","https://openalex.org/W6850218400","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4391272374","https://openalex.org/W4403759994","https://openalex.org/W4400309480","https://openalex.org/W2081919107"],"abstract_inverted_index":{"Collecting":[0],"high-quality":[1],"studio":[2],"recordings":[3],"of":[4,13,85,94],"audio":[5],"is":[6],"challenging,":[7],"which":[8],"limits":[9],"the":[10,101,109,117],"language":[11],"coverage":[12],"text-to-speech":[14],"(TTS)":[15],"systems.":[16],"This":[17],"paper":[18],"proposes":[19],"a":[20,24,69],"framework":[21,38],"for":[22],"scaling":[23],"multilingual":[25,57],"TTS":[26,73],"model":[27,74],"to":[28,87,104],"100+":[29],"languages":[30,82],"using":[31,46],"found":[32,96],"data":[33,52],"without":[34],"supervision.":[35],"The":[36],"proposed":[37],"combines":[39],"speech-text":[40],"encoder":[41],"pretraining":[42],"with":[43],"unsupervised":[44],"training":[45],"untranscribed":[47],"speech":[48,59,67,78],"and":[49,60,111],"unspoken":[50],"text":[51,61],"sources,":[53],"thereby":[54],"leveraging":[55],"massively":[56],"joint":[58],"representation":[62],"learning.":[63],"Without":[64],"any":[65],"transcribed":[66],"in":[68,79,119],"new":[70],"language,":[71],"this":[72],"can":[75,99],"generate":[76],"intelligible":[77],">30":[80],"unseen":[81],"(CER":[83],"difference":[84,103],"<10%":[86],"ground":[88],"truth).":[89],"With":[90],"just":[91],"15":[92],"minutes":[93],"transcribed,":[95],"data,":[97],"we":[98],"reduce":[100],"intelligibility":[102],"1%":[105],"or":[106],"less":[107],"from":[108],"ground-truth,":[110],"achieve":[112],"naturalness":[113],"scores":[114],"that":[115],"match":[116],"ground-truth":[118],"several":[120],"languages.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}