{"id":"https://openalex.org/W4403826735","doi":"https://doi.org/10.1109/access.2024.3487053","title":"Applying Syntax-Prosody Mapping Hypothesis and Boundary-Driven Theory to Neural Sequence-to-Sequence Speech Synthesis","display_name":"Applying Syntax-Prosody Mapping Hypothesis and Boundary-Driven Theory to Neural Sequence-to-Sequence Speech Synthesis","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403826735","doi":"https://doi.org/10.1109/access.2024.3487053"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3487053","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3487053","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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://doi.org/10.1109/access.2024.3487053","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101153319","display_name":"Kei Furukawa","orcid":"https://orcid.org/0009-0002-0100-7450"},"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":"Kei Furukawa","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/A5064856959","display_name":"Takeshi Kishiyama","orcid":"https://orcid.org/0000-0001-5462-4351"},"institutions":[{"id":"https://openalex.org/I165953009","display_name":"Tokyo University of the Arts","ror":"https://ror.org/00y809n33","country_code":"JP","type":"education","lineage":["https://openalex.org/I165953009"]},{"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":"Takeshi Kishiyama","raw_affiliation_strings":["Graduate School of Arts and Sciences, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Arts and Sciences, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I165953009","https://openalex.org/I74801974"]}]},{"author_position":"middle","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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"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":"Sakriani Sakti","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":4,"corresponding_author_ids":["https://openalex.org/A5101153319"],"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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16639316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"160896","last_page":"160917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9671000242233276,"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":0.9671000242233276,"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":0.9490000009536743,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9455000162124634,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7669057250022888},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7536249756813049},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7211529016494751},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5959087610244751},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5358195900917053},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5100999474525452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5087748169898987},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5032984614372253}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7669057250022888},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7536249756813049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7211529016494751},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5959087610244751},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5358195900917053},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5100999474525452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5087748169898987},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5032984614372253},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2024.3487053","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3487053","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7460cdbb60884b8387117726720d94d6","is_oa":true,"landing_page_url":"https://doaj.org/article/7460cdbb60884b8387117726720d94d6","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 12, Pp 160896-160917 (2024)","raw_type":"article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0007213661","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/2001295","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2024.3487053","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3487053","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G5172868567","display_name":null,"funder_award_id":"JPMJSP2140","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"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"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W30677081","https://openalex.org/W1591266773","https://openalex.org/W1608101656","https://openalex.org/W1714605128","https://openalex.org/W1987515642","https://openalex.org/W1991784890","https://openalex.org/W2056501378","https://openalex.org/W2101992199","https://openalex.org/W2271507464","https://openalex.org/W2274404631","https://openalex.org/W2498996464","https://openalex.org/W2509327498","https://openalex.org/W2532186569","https://openalex.org/W2605022468","https://openalex.org/W2742290625","https://openalex.org/W2749069611","https://openalex.org/W2903739847","https://openalex.org/W2962758893","https://openalex.org/W2962780374","https://openalex.org/W2963945466","https://openalex.org/W2964243274","https://openalex.org/W2972831865","https://openalex.org/W2972885185","https://openalex.org/W3008266717","https://openalex.org/W3015338123","https://openalex.org/W3128170746","https://openalex.org/W3214743865","https://openalex.org/W4206003764","https://openalex.org/W4213044147","https://openalex.org/W4231324690","https://openalex.org/W4297841637","https://openalex.org/W4390911400","https://openalex.org/W4393657918","https://openalex.org/W4402037708","https://openalex.org/W6602009891","https://openalex.org/W6609129650","https://openalex.org/W6636118370","https://openalex.org/W6684830645","https://openalex.org/W6687007940","https://openalex.org/W6762891684","https://openalex.org/W6778823374","https://openalex.org/W6797107937"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","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":{"This":[0,53,101,145,179],"study":[1,54],"presents":[2],"a":[3,67,95,127,183],"novel":[4],"approach":[5,158],"to":[6,106,118],"Japanese":[7,61,99],"speech":[8,62,155,164,193],"synthesis":[9],"by":[10,170],"applying":[11],"the":[12,17,25,37,76,88,103,124,132,142,148,168,176,187],"syntax-prosody":[13],"mapping":[14],"hypothesis":[15],"and":[16,31,49,70,90,189,201],"boundary-driven":[18],"theory,":[19],"both":[20,47,87],"from":[21],"linguistics.":[22],"Focusing":[23],"on":[24],"phonological":[26,121,152],"phenomena":[27],"of":[28,78,92,150,192],"initial":[29,93],"lowering":[30],"rhythmic":[32,133,137],"boost,":[33],"our":[34],"research":[35,180],"introduces":[36],"Recursive":[38,82],"Phonological":[39,83],"Model,":[40],"which":[41],"significantly":[42],"outperforms":[43],"traditional":[44],"methods":[45],"in":[46,98,130,141,154,175,186],"objective":[48,57],"subjective":[50],"evaluation":[51,58],"experiments.":[52],"proposes":[55],"new":[56],"criteria":[59,65],"for":[60,74,198],"synthesis.":[63,156],"These":[64],"offer":[66],"more":[68,162],"rigorous":[69],"linguistically":[71],"grounded":[72],"methodology":[73],"assessing":[75],"quality":[77],"synthesized":[79],"speech.":[80,100],"The":[81],"Model":[84],"accurately":[85],"captures":[86],"presence":[89],"absence":[91],"lowering,":[94],"common":[96],"phenomenon":[97],"is":[102],"first":[104],"model":[105,125],"successfully":[107],"reflect":[108],"such":[109],"syntactic":[110],"variations":[111],"through":[112],"intonation,":[113],"demonstrating":[114],"its":[115],"advanced":[116],"ability":[117,146],"handle":[119],"complex":[120,172],"patterns.":[122],"Additionally,":[123],"demonstrates":[126],"unique":[128],"proficiency":[129],"reproducing":[131],"boost":[134,138],"phenomenon,":[135],"despite":[136],"being":[139],"absent":[140],"training":[143],"data.":[144],"underscores":[147],"importance":[149],"learning":[151],"boundaries":[153],"Our":[157],"not":[159],"only":[160],"yields":[161],"natural-sounding":[163],"but":[165],"also":[166],"enriches":[167],"field":[169],"incorporating":[171],"linguistic":[173,190],"theories":[174],"computational":[177,199],"process.":[178],"thus":[181],"marks":[182],"significant":[184],"advance":[185],"naturalness":[188],"accuracy":[191],"synthesis,":[194],"with":[195],"broader":[196],"implications":[197],"linguistics":[200],"artificial":[202],"intelligence.":[203]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}