{"id":"https://openalex.org/W4411949025","doi":"https://doi.org/10.1109/access.2025.3585135","title":"Phoneme-Level Duration Controllable Neural Text-to-Speech With Phoneme Embedding Skip Connection and Modified Gaussian Duration Modeling","display_name":"Phoneme-Level Duration Controllable Neural Text-to-Speech With Phoneme Embedding Skip Connection and Modified Gaussian Duration Modeling","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411949025","doi":"https://doi.org/10.1109/access.2025.3585135"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3585135","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3585135","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.2025.3585135","any_repository_has_fulltext":true},"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, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4507-0008","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, 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, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9913-4647","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, 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, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0009-0009-2961-2821","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, 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, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, 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/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":"Tomoki Toda","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8146-1279","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"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, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0914-5092","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84506045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"13","issue":null,"first_page":"118369","last_page":"118380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9987000226974487,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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/duration","display_name":"Duration (music)","score":0.8436264991760254},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6892600655555725},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.648905336856842},{"id":"https://openalex.org/keywords/connection","display_name":"Connection (principal bundle)","score":0.6295462250709534},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.46170666813850403},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4485052824020386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.327578604221344},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.191879540681839},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19074994325637817},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07580861449241638}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.8436264991760254},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6892600655555725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.648905336856842},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.6295462250709534},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.46170666813850403},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4485052824020386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.327578604221344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.191879540681839},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19074994325637817},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07580861449241638},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3585135","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3585135","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:7f05309178c24390972809120859dccc","is_oa":true,"landing_page_url":"https://doaj.org/article/7f05309178c24390972809120859dccc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 118369-118380 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3585135","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3585135","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W133559434","https://openalex.org/W276137422","https://openalex.org/W1494198834","https://openalex.org/W1541019354","https://openalex.org/W1576227399","https://openalex.org/W2030639849","https://openalex.org/W2072274775","https://openalex.org/W2102003408","https://openalex.org/W2106792148","https://openalex.org/W2114174754","https://openalex.org/W2168510624","https://openalex.org/W2278339107","https://openalex.org/W2519091744","https://openalex.org/W2586453598","https://openalex.org/W2747070883","https://openalex.org/W2747874407","https://openalex.org/W2769810959","https://openalex.org/W2794139017","https://openalex.org/W2903739847","https://openalex.org/W2938102059","https://openalex.org/W2964243274","https://openalex.org/W3007859642","https://openalex.org/W3094650042","https://openalex.org/W3097777922","https://openalex.org/W3128170746","https://openalex.org/W3161296985","https://openalex.org/W3161782335","https://openalex.org/W3163793923","https://openalex.org/W3196001064","https://openalex.org/W3197294703","https://openalex.org/W3198843334","https://openalex.org/W3206375275","https://openalex.org/W4210287297","https://openalex.org/W4210633887","https://openalex.org/W4221152438","https://openalex.org/W4224612669","https://openalex.org/W4224931655","https://openalex.org/W4225956675","https://openalex.org/W4312443924","https://openalex.org/W4319862245","https://openalex.org/W4372270423","https://openalex.org/W4372341178","https://openalex.org/W4385245566","https://openalex.org/W4391021821","https://openalex.org/W4391892412","https://openalex.org/W4392903256","https://openalex.org/W6607249510","https://openalex.org/W6763832098","https://openalex.org/W6766978945","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6779337556","https://openalex.org/W6779469704","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6802659129","https://openalex.org/W6805710207","https://openalex.org/W6851724922"],"related_works":["https://openalex.org/W2348837382","https://openalex.org/W746329893","https://openalex.org/W4205872570","https://openalex.org/W4245971243","https://openalex.org/W587735977","https://openalex.org/W1922805944","https://openalex.org/W2081900870","https://openalex.org/W4253588120","https://openalex.org/W1978142926","https://openalex.org/W2383732295"],"abstract_inverted_index":{"This":[0],"paper":[1,68,130],"proposes":[2,131],"a":[3,70,94],"simple":[4,35,95,215],"but":[5,143],"practically":[6],"important":[7],"and":[8,16,38,46,60,98,125,174,185,194,214,217,225],"effective":[9],"approach":[10],"to":[11],"improve":[12,116,163],"phoneme":[13,57,71,122,148],"duration":[14,123,134,170,183,188,222,236],"expansion":[15,37,45,124,171,216,237],"contraction":[17,39,126,218,223],"control":[18,184,189],"in":[19,58,77,88],"neural":[20,89,151,196],"text-to-speech":[21],"(TTS)":[22],"systems":[23],"for":[24,55,121,150,168,179,220,234],"modifying":[25],"the":[26,44,84,107,111,117,158,164,169,202,221,231,235],"speaking":[27],"rate":[28],"of":[29,34,49,147,201],"synthesized":[30,118,165],"speech.":[31],"The":[32,199],"use":[33],"uniform":[36],"is":[40],"sometimes":[41],"unnatural":[42],"because":[43],"compression":[47],"rates":[48],"actual":[50],"human":[51],"speech":[52,119,166],"are":[53,81,177],"different":[54],"each":[56],"fast":[59],"slow":[61],"conditions.":[62,127],"To":[63],"address":[64],"this":[65,67,129],"problem,":[66],"introduces":[69],"embedding":[72],"skip":[73,96],"connection":[74],"technique":[75],"(PESC),":[76],"which":[78,137],"phoneme-level":[79,99,108],"embeddings":[80],"added":[82],"with":[83,156,191,228],"encoder":[85],"output":[86],"features":[87],"TTS":[90,152,197],"acoustic":[91,153],"models":[92],"by":[93],"connection,":[97],"components":[100,109],"can":[101,115,161],"then":[102],"be":[103],"enhanced.":[104],"By":[105],"enhancing":[106],"before":[110],"length":[112],"regulator,":[113],"PESC":[114,206,227],"quality":[120,167],"Additionally,":[128],"modified":[132,159],"Gaussian":[133],"modeling":[135],"(GDM),":[136],"predicts":[138],"not":[139],"only":[140],"mean":[141],"values":[142,146],"also":[144],"variance":[145],"durations,":[149],"models.":[154],"Combined":[155],"PESC,":[157],"GDM":[160,208,229],"further":[162],"condition.":[172,238],"Objective":[173],"subjective":[175],"experiments":[176,203],"conducted":[178],"both":[180,192],"whole":[181],"sentence":[182],"partial":[186],"utterance":[187],"conditions":[190],"Japanese":[193],"English":[195],"systems.":[198],"results":[200],"demonstrate":[204],"that":[205,226],"without":[207],"outperforms":[209,230],"conventional":[210,232],"WSOLA,":[211],"feature":[212],"interpolation,":[213],"methods":[219,233],"condition,":[224]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}