{"id":"https://openalex.org/W4323022342","doi":"https://doi.org/10.1109/access.2023.3251657","title":"Japanese Neural Incremental Text-to-Speech Synthesis Framework With an Accent Phrase Input","display_name":"Japanese Neural Incremental Text-to-Speech Synthesis Framework With an Accent Phrase Input","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4323022342","doi":"https://doi.org/10.1109/access.2023.3251657"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3251657","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3251657","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10057419.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10057419.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067528281","display_name":"Tomoya Yanagita","orcid":"https://orcid.org/0000-0001-8250-6088"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tomoya Yanagita","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067528281"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.3442,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62985327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"11","issue":null,"first_page":"22355","last_page":"22363"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.7816280126571655},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7769575119018555},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7434120178222656},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6402203440666199},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5903890132904053},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5895103216171265},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5526448488235474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7816280126571655},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7769575119018555},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7434120178222656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6402203440666199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5903890132904053},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5895103216171265},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5526448488235474}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2023.3251657","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3251657","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10057419.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6e1833deb71d4af3ab6481fd9421e776","is_oa":true,"landing_page_url":"https://doaj.org/article/6e1833deb71d4af3ab6481fd9421e776","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 22355-22363 (2023)","raw_type":"article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0006019370","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/2000110","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3251657","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3251657","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10057419.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"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/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3670916553","display_name":null,"funder_award_id":"21H05","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4227499671","display_name":null,"funder_award_id":"KAKENHI Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4827429566","display_name":null,"funder_award_id":"Grant Numbers","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5786340949","display_name":null,"funder_award_id":"KAKENHI Grant Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7236939988","display_name":null,"funder_award_id":"JP21H03467","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7752643416","display_name":null,"funder_award_id":"Japan","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7893352204","display_name":null,"funder_award_id":"JP21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8843746042","display_name":null,"funder_award_id":"JP21H0505","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"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/W4323022342.pdf","grobid_xml":"https://content.openalex.org/works/W4323022342.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W44352932","https://openalex.org/W195154367","https://openalex.org/W344150399","https://openalex.org/W1576227399","https://openalex.org/W2003791490","https://openalex.org/W2102003408","https://openalex.org/W2107860279","https://openalex.org/W2136545725","https://openalex.org/W2273480558","https://openalex.org/W2517566275","https://openalex.org/W2519091744","https://openalex.org/W2765486990","https://openalex.org/W2886769154","https://openalex.org/W2889095150","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2963945466","https://openalex.org/W2964243274","https://openalex.org/W2972831865","https://openalex.org/W2972895078","https://openalex.org/W3015282541","https://openalex.org/W3015338123","https://openalex.org/W3048023795","https://openalex.org/W3083224111","https://openalex.org/W3092316169","https://openalex.org/W3104081910","https://openalex.org/W3114579299","https://openalex.org/W3128170746","https://openalex.org/W3156563027","https://openalex.org/W3197407562","https://openalex.org/W6631190155","https://openalex.org/W6745289305","https://openalex.org/W6748409065","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6843673214"],"related_works":["https://openalex.org/W4367680763","https://openalex.org/W2739335048","https://openalex.org/W1506224037","https://openalex.org/W4213177143","https://openalex.org/W2151922127","https://openalex.org/W2039546652","https://openalex.org/W4237818736","https://openalex.org/W4252005663","https://openalex.org/W2365914832","https://openalex.org/W4379055549"],"abstract_inverted_index":{"Work":[0],"in":[1,187,211],"the":[2,23,52,83,107,113,117,122,129,148,164,181,188,196,208],"development":[3],"of":[4,42,131,203],"neural":[5,37,69,85,168],"incremental":[6,201],"text-to-speech":[7],"(iTTS),":[8],"which":[9],"is":[10,55,151],"attracting":[11],"increasing":[12],"attention,":[13],"has":[14],"recently":[15],"pursued":[16],"low-latency":[17],"processing":[18],"by":[19,111],"generating":[20],"speech":[21,96,156],"on":[22,57],"fly":[24],"before":[25],"reading":[26],"complete":[27],"sentences.":[28],"Most":[29],"current":[30,123],"state-of-the-art":[31],"iTTS":[32,38,70,86,133,150,169,213],"systems":[33,134],"use":[34,104],"a":[35,67,72,101,159],"prefix-to-prefix":[36,68,167],"framework":[39],"with":[40,71,135,158,170,199],"look-ahead":[41,73,92],"1-2":[43],"unit":[44,202],"segments":[45],"(i.e.,":[46],"phonemes":[47],"or":[48],"words).":[49],"However,":[50],"since":[51],"Japanese":[53,189,212],"language":[54],"based":[56],"accent":[58,205],"phrase":[59],"units":[60,186],"that":[61,88,176,195],"are":[62],"longer":[63],"than":[64,163],"words,":[65],"using":[66],"approach":[74,179,198],"increases":[75],"latency.":[76],"Here,":[77],"we":[78,174],"propose":[79,100],"an":[80,200],"alternative":[81],"to":[82,103,121,153],"end-to-end":[84],"architecture":[87],"does":[89],"not":[90],"apply":[91],"input":[93],"when":[94],"synthesizing":[95],"chunks.":[97,140],"We":[98,126],"further":[99],"method":[102],"information":[105],"from":[106],"previous":[108],"time":[109,124],"step":[110],"connecting":[112],"synthesized":[114,185],"vector":[115],"and":[116,138],"model\u2019s":[118],"internal":[119],"state":[120],"step.":[125],"experimentally":[127],"investigated":[128],"latency":[130,161],"various":[132],"different":[136],"modeling":[137],"synthesis":[139],"The":[141],"experimental":[142],"results":[143],"show":[144],"that,":[145],"for":[146],"Japanese,":[147],"proposed":[149,178,197],"able":[152],"synthesize":[154],"better":[155],"quality,":[157],"similar":[160],"range,":[162],"conventional":[165],"baseline":[166],"word":[171],"units.":[172],"Moreover,":[173],"found":[175],"our":[177],"improved":[180],"prosodic":[182],"naturalness":[183],"among":[184],"language.":[190],"Subjective":[191],"evaluations":[192],"also":[193],"revealed":[194],"two":[204],"phrases":[206],"achieved":[207],"best":[209],"scores":[210],"systems.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
