{"id":"https://openalex.org/W4392114301","doi":"https://doi.org/10.1109/taslp.2024.3369537","title":"Text-Inductive Graphone-Based Language Adaptation for Low-Resource Speech Synthesis","display_name":"Text-Inductive Graphone-Based Language Adaptation for Low-Resource Speech Synthesis","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392114301","doi":"https://doi.org/10.1109/taslp.2024.3369537"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3369537","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3369537","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10444075.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10444075.pdf","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":true,"raw_author_name":"Takaaki Saeki","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6003-768X","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010858961","display_name":"Soumi Maiti","orcid":"https://orcid.org/0000-0001-6940-0115"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumi Maiti","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technologies Institute, Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6940-0115","affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100660610","display_name":"Xinjian Li","orcid":"https://orcid.org/0000-0003-4585-159X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinjian Li","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technologies Institute, Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4585-159X","affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technologies Institute, Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5970-8631","affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"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":"Shinnosuke Takamichi","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0520-7847","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"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":"Hiroshi Saruwatari","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0876-5617","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5025983709"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":3.3114,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.9266304,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"1829","last_page":"1844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"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":0.9955999851226807,"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":0.9833999872207642,"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":0.9570000171661377,"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/adaptation","display_name":"Adaptation (eye)","score":0.7386471629142761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5519303679466248},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5124314427375793},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.46610862016677856},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34174615144729614},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3317488431930542},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.304363876581192}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7386471629142761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5519303679466248},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5124314427375793},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.46610862016677856},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34174615144729614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3317488431930542},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.304363876581192},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/taslp.2024.3369537","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3369537","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10444075.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2024.3369537","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3369537","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10444075.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2363020693","display_name":null,"funder_award_id":"21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7404166632","display_name":"Bridges: From Communities and Data to Workflows and Insight","funder_award_id":"1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8729765517","display_name":null,"funder_award_id":"ACI-1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392114301.pdf","grobid_xml":"https://content.openalex.org/works/W4392114301.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W1526974435","https://openalex.org/W2025638820","https://openalex.org/W2058094241","https://openalex.org/W2090755665","https://openalex.org/W2093450784","https://openalex.org/W2106568252","https://openalex.org/W2140576685","https://openalex.org/W2144994235","https://openalex.org/W2182894058","https://openalex.org/W2494654097","https://openalex.org/W2726515241","https://openalex.org/W2746132399","https://openalex.org/W2769280657","https://openalex.org/W2889028433","https://openalex.org/W2896457183","https://openalex.org/W2901389167","https://openalex.org/W2903739847","https://openalex.org/W2952638691","https://openalex.org/W2962780374","https://openalex.org/W2964002616","https://openalex.org/W2970854433","https://openalex.org/W2972359262","https://openalex.org/W2972802841","https://openalex.org/W2973034126","https://openalex.org/W2973217961","https://openalex.org/W3016160783","https://openalex.org/W3034469191","https://openalex.org/W3035390927","https://openalex.org/W3048217770","https://openalex.org/W3082130377","https://openalex.org/W3096303254","https://openalex.org/W3101498587","https://openalex.org/W3104723404","https://openalex.org/W3105421296","https://openalex.org/W3114579299","https://openalex.org/W3119308075","https://openalex.org/W3156563027","https://openalex.org/W3163339651","https://openalex.org/W3167533889","https://openalex.org/W3174758275","https://openalex.org/W3177252310","https://openalex.org/W3181257032","https://openalex.org/W3197324626","https://openalex.org/W3206375275","https://openalex.org/W4230579319","https://openalex.org/W4285181910","https://openalex.org/W4285189120","https://openalex.org/W4292341621","https://openalex.org/W4296068816","https://openalex.org/W4296069143","https://openalex.org/W4297841354","https://openalex.org/W4311000453","https://openalex.org/W4319862635","https://openalex.org/W4372183701","https://openalex.org/W4375869005","https://openalex.org/W4385245566","https://openalex.org/W4385764360","https://openalex.org/W4385993876","https://openalex.org/W6610006008","https://openalex.org/W6638665372","https://openalex.org/W6731979058","https://openalex.org/W6757094361","https://openalex.org/W6767737316","https://openalex.org/W6770212971","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6796730497","https://openalex.org/W6798575157","https://openalex.org/W6802659129","https://openalex.org/W6846288075","https://openalex.org/W6847363464","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W1533421371","https://openalex.org/W2003050223","https://openalex.org/W2091777911","https://openalex.org/W2766405861","https://openalex.org/W2360975119","https://openalex.org/W2912421143","https://openalex.org/W2372487155"],"abstract_inverted_index":{"Neural":[0],"text-to-speech":[1],"(TTS)":[2],"systems":[3],"have":[4],"made":[5],"significant":[6],"progress":[7],"in":[8],"generating":[9],"natural":[10],"synthetic":[11,257],"speech.":[12],"However,":[13],"neural":[14],"TTS":[15,38,82,151,238],"requires":[16],"large":[17],"amounts":[18],"of":[19,31,63,87,198,235,247,264],"paired":[20,64,90,156,248],"training":[21,168,229],"data,":[22],"which":[23],"limits":[24],"its":[25],"applicability":[26],"to":[27,52,83,180,203],"a":[28,49,75,105,132,165,269],"small":[29],"number":[30],"resource-rich":[32,184,202],"languages.":[33,69,94,192,205],"Previous":[34],"work":[35],"on":[36,45,60],"low-resource":[37,53,81,93,191,204,240],"has":[39],"addressed":[40],"the":[41,61,67,85,89,117,121,127,141,145,149,159,196,219,226,233,260],"data":[42,65,91,115,139,157,249],"hungriness":[43],"based":[44],"transfer":[46,100,197,222],"learning":[47,223],"from":[48,201],"multilingual":[50,167,237],"model":[51,135,152],"languages,":[54,185],"but":[55],"it":[56],"still":[57],"relies":[58],"heavily":[59],"availability":[62],"for":[66,80,92,116,140,158,183,190,250,268],"target":[68,118,142,160,270],"In":[70,120,144],"this":[71],"paper,":[72],"we":[73,125,209],"propose":[74,164],"text-inductive":[76],"language":[77,134,241],"adaptation":[78,107,123,147,217],"framework":[79,103,214],"address":[84],"cost":[86],"collecting":[88],"To":[95],"inject":[96],"textual":[97],"knowledge":[98,200],"during":[99],"learning,":[101],"our":[102,213,252],"employs":[104],"two-stage":[106],"scheme":[108],"that":[109,170,211],"utilizes":[110],"both":[111,236],"text-only":[112,138],"and":[113,174,239],"supervised":[114,146,221],"language.":[119,143,161,271],"text-based":[122,216],"stage,":[124,148],"update":[126],"language-aware":[128],"embedding":[129],"layer":[130],"with":[131,215,259],"masked":[133],"objective":[136],"using":[137,155,187],"entire":[150],"is":[153],"updated":[154],"We":[162],"also":[163],"graphone-based":[166,228],"method":[169,230,253],"jointly":[171],"uses":[172],"graphemes":[173,189],"International":[175],"Phonetic":[176],"Alphabet":[177],"symbols":[178],"(referred":[179],"as":[181],"graphones)":[182],"while":[186],"only":[188,244],"This":[193],"approach":[194],"facilitates":[195],"pronunciation":[199],"Through":[206],"extensive":[207],"evaluations,":[208],"demonstrate":[210],"1)":[212],"outperforms":[218],"previous":[220],"approach,":[224],"2)":[225],"proposed":[227],"further":[231],"improves":[232],"performance":[234],"adaptation.":[242],"With":[243],"5":[245],"minutes":[246],"fine-tuning,":[251],"achieved":[254],"highly":[255],"intelligible":[256],"speech":[258],"character":[261],"error":[262],"rates":[263],"around":[265],"6":[266],"%":[267]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}