{"id":"https://openalex.org/W4416798855","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249200","title":"MixedG2P-T5: G2P-Free Speech Synthesis for Mixed-Script Texts Using Speech Self-Supervised Learning and Language Model","display_name":"MixedG2P-T5: G2P-Free Speech Synthesis for Mixed-Script Texts Using Speech Self-Supervised Learning and Language Model","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798855","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249200"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","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/A5109692719","display_name":"Joonyong Park","orcid":null},"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":"Joonyong Park","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010715755","display_name":"Daisuke Saito","orcid":"https://orcid.org/0000-0003-3012-1607"},"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":"Daisuke Saito","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"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":"Nobuaki Minematsu","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1728311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"765","last_page":"770"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8723999857902527,"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":0.8723999857902527,"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/T10863","display_name":"Voice and Speech Disorders","score":0.03139999881386757,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.009999999776482582,"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/paralanguage","display_name":"Paralanguage","score":0.7339000105857849},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6363000273704529},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4745999872684479},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4174000024795532},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.39250001311302185},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.35760000348091125},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.35030001401901245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831000089645386},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.7339000105857849},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.671500027179718},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6363000273704529},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.552299976348877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4814999997615814},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.35030001401901245},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3199000060558319},{"id":"https://openalex.org/C83535845","wikidata":"https://www.wikidata.org/wiki/Q82772","display_name":"Kanji","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3084999918937683},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2964243274","https://openalex.org/W2972903407","https://openalex.org/W3037482713","https://openalex.org/W3169483174","https://openalex.org/W3196027980","https://openalex.org/W3198848374","https://openalex.org/W3205644108","https://openalex.org/W3209059054","https://openalex.org/W4224629880","https://openalex.org/W4225956675","https://openalex.org/W4292264739","https://openalex.org/W4296068769","https://openalex.org/W4296068791"],"related_works":[],"abstract_inverted_index":{"This":[0,53],"study":[1],"presents":[2],"a":[3,19,31,38],"novel":[4],"approach":[5],"to":[6,41],"voice":[7,33],"synthesis":[8],"that":[9,23,89],"can":[10],"substitute":[11],"the":[12,56,76],"traditional":[13],"grapheme-to-phoneme":[14],"(G2P)":[15],"conversion":[16],"by":[17],"using":[18],"deep":[20],"learning-based":[21],"model":[22,74],"generates":[24],"discrete":[25],"tokens":[26],"directly":[27],"from":[28,45],"speech.":[29],"Utilizing":[30],"pretrained":[32],"SSL":[34],"model,":[35],"we":[36],"train":[37],"T5":[39],"encoder":[40],"produce":[42],"pseudo-language":[43],"labels":[44],"mixed-script":[46],"texts":[47],"(e.g.,":[48],"containing":[49],"Kanji":[50],"and":[51,64,83,93,99],"Kana).":[52],"method":[54],"eliminates":[55],"need":[57],"for":[58,68],"manual":[59],"phonetic":[60],"transcription,":[61],"reducing":[62],"costs":[63],"enhancing":[65],"scalability,":[66],"especially":[67],"large":[69],"non-transcribed":[70],"audio":[71],"datasets.":[72],"Our":[73],"matches":[75],"performance":[77],"of":[78,86],"conventional":[79],"G2P-based":[80],"text-tospeech":[81],"systems":[82],"is":[84],"capable":[85],"synthesizing":[87],"speech":[88],"retains":[90],"natural":[91],"linguistic":[92],"paralinguistic":[94],"features,":[95],"such":[96],"as":[97],"accents":[98],"intonations.":[100]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}