{"id":"https://openalex.org/W4408354975","doi":"https://doi.org/10.1109/icassp49660.2025.10887607","title":"Mora-Level Prosody Prediction for Text-to-Speech Using Japanese BERT Without Accentual Labels","display_name":"Mora-Level Prosody Prediction for Text-to-Speech Using Japanese BERT Without Accentual Labels","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354975","doi":"https://doi.org/10.1109/icassp49660.2025.10887607"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5036541995","display_name":"Tadashi Ogura","orcid":"https://orcid.org/0000-0002-4507-0008"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tadashi Ogura","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022943637","display_name":"Takuma Okamoto","orcid":"https://orcid.org/0000-0001-9913-4647"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuma Okamoto","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018533235","display_name":"Yamato Ohtani","orcid":"https://orcid.org/0009-0009-2961-2821"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yamato Ohtani","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082349516","display_name":"Erica Cooper","orcid":"https://orcid.org/0000-0002-2978-2793"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Erica Cooper","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114514387","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.9901000261306763,"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":0.9901000261306763,"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":0.9876999855041504,"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":0.9818000197410583,"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/prosody","display_name":"Prosody","score":0.8174178600311279},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6597151756286621},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5502918362617493},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.53458571434021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5030407309532166},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4152894616127014}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8174178600311279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6597151756286621},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5502918362617493},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.53458571434021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5030407309532166},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4152894616127014}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":39,"referenced_works":["https://openalex.org/W1541019354","https://openalex.org/W2747070883","https://openalex.org/W2940200615","https://openalex.org/W2963945466","https://openalex.org/W2964243274","https://openalex.org/W2973217961","https://openalex.org/W3015727134","https://openalex.org/W3016137096","https://openalex.org/W3081488690","https://openalex.org/W3081800019","https://openalex.org/W3128170746","https://openalex.org/W3150572638","https://openalex.org/W3163793923","https://openalex.org/W3196001064","https://openalex.org/W3196875702","https://openalex.org/W3197324626","https://openalex.org/W4224612669","https://openalex.org/W4253028564","https://openalex.org/W4285412695","https://openalex.org/W4385245566","https://openalex.org/W4385569771","https://openalex.org/W4385571689","https://openalex.org/W4389520370","https://openalex.org/W4390480998","https://openalex.org/W4391892412","https://openalex.org/W4392903256","https://openalex.org/W4401597514","https://openalex.org/W4402111994","https://openalex.org/W4402112526","https://openalex.org/W6726491551","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6766978945","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6779469704","https://openalex.org/W6796464841","https://openalex.org/W6802659129","https://openalex.org/W6851724922"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"abstract_inverted_index":{"In":[0],"practical":[1],"text-to-speech":[2],"(TTS)":[3],"for":[4,70,90,135,149],"pitch":[5],"accent":[6,33,42,57,66,240],"languages,":[7],"such":[8],"as":[9,167,179],"Japanese,":[10],"high-fidelity":[11],"synthesis":[12,213,236],"with":[13,47,111,157,206,243,248],"correct":[14,211],"prosody":[15,87],"requires":[16],"not":[17,36,99],"only":[18],"a":[19,85,143],"phoneme":[20],"sequence":[21,191],"but":[22],"also":[23,72],"accentual":[24,27,78,102,249],"information.":[25],"Although":[26],"information":[28,67],"can":[29,214,232],"be":[30,215],"obtained":[31],"from":[32],"dictionaries,":[34],"words":[35],"included":[37],"in":[38],"the":[39,131,136,150,163,170,180,186,194,201,207,229,234],"dictionaries":[40],"and":[41,50,97,119,162,169,210,238],"sandhi":[43],"are":[44,133],"sometimes":[45],"synthesized":[46],"incorrect":[48],"prosody,":[49,132],"manual":[51],"registration":[52],"of":[53,56,76],"huge":[54,74],"amounts":[55],"data":[58,138],"is":[59,116,147,198],"costly.":[60],"Additionally,":[61],"previous":[62],"machine":[63],"learning-based":[64],"data-driven":[65,86],"estimation":[68],"approaches":[69],"TTS":[71,92,108,184,202,246],"require":[73,100],"quantities":[75],"handcrafted":[77],"labels":[79,103],"during":[80,104],"training.":[81,105],"This":[82],"paper":[83],"proposes":[84],"prediction":[88,155,181],"method":[89,231],"Japanese":[91,95,107,145,196],"that":[93,228],"uses":[94],"BERT":[96,146,197],"does":[98],"any":[101],"A":[106],"acoustic":[109,203],"model":[110,204],"mora-level":[112,120,151,171,187],"(katakana":[113],"sequence)":[114],"input":[115,168,199],"first":[117],"trained":[118],"fundamental":[121],"frequency":[122],"values":[123],"(f<inf":[124],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[125,153,173,189,222],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">o</inf>),":[126],"which":[127],"directly":[128],"correspond":[129],"to":[130,200,218],"extracted":[134,175],"training":[137],"using":[139,176],"forced":[140,177],"alignment.":[141],"Then,":[142],"pre-trained":[144],"finetuned":[148,195],"f<inf":[152,172,188,221],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">o</inf>":[154,174,190,223],"task":[156],"word":[158],"sequences":[159,166],"including":[160],"kanji":[161],"corresponding":[164],"katakana":[165,208],"alignment":[178],"target.":[182],"During":[183],"inference,":[185],"predicted":[192,220],"by":[193],"along":[205],"input,":[209],"prosodic":[212],"realized":[216],"thanks":[217],"this":[219],"sequence.":[224],"Experimental":[225],"results":[226],"demonstrate":[227],"proposed":[230],"realize":[233],"same":[235],"quality":[237],"higher":[239],"correctness":[241],"compared":[242],"conventional":[244],"neural":[245],"models":[247],"labels.":[250]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}