{"id":"https://openalex.org/W7130392796","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385230","title":"Toward Natural Emotional Text-to-Speech System with Fine-Grained Non-Verbal Expression Control","display_name":"Toward Natural Emotional Text-to-Speech System with Fine-Grained Non-Verbal Expression Control","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7130392796","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385230"},"language":null,"primary_location":{"id":"doi:10.1109/o-cocosda68185.2025.11385230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2605.25504","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126292799","display_name":"Wangzixi Zhou","orcid":null},"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":"Wangzixi Zhou","raw_affiliation_strings":["Nara Institute of Science and Technology,Ikoma,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Ikoma,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065879041","display_name":"Bagus Tris Atmaja","orcid":"https://orcid.org/0000-0003-1560-2824"},"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":"Bagus Tris Atmaja","raw_affiliation_strings":["Nara Institute of Science and Technology,Ikoma,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Ikoma,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,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Ikoma,Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8400999903678894,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8400999903678894,"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"}},{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.06530000269412994,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.019099999219179153,"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/sadness","display_name":"Sadness","score":0.9065999984741211},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.58160001039505},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5282999873161316},{"id":"https://openalex.org/keywords/emotional-expression","display_name":"Emotional expression","score":0.5254999995231628},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5024999976158142},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.44600000977516174},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.42910000681877136}],"concepts":[{"id":"https://openalex.org/C2779812673","wikidata":"https://www.wikidata.org/wiki/Q169251","display_name":"Sadness","level":3,"score":0.9065999984741211},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.58160001039505},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5550000071525574},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5282999873161316},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.5254999995231628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5192000269889832},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4684000015258789},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C145633318","wikidata":"https://www.wikidata.org/wiki/Q207125","display_name":"Nonverbal communication","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.36489999294281006},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C2778143943","wikidata":"https://www.wikidata.org/wiki/Q523747","display_name":"Expressed emotion","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2549000084400177}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/o-cocosda68185.2025.11385230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2605.25504","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.25504","pdf_url":"https://arxiv.org/pdf/2605.25504","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2605.25504","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.25504","pdf_url":"https://arxiv.org/pdf/2605.25504","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5712634325027466,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[{"id":"https://openalex.org/G1435354637","display_name":null,"funder_award_id":"JP23K21681","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"}],"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/W7130392796.pdf","grobid_xml":"https://content.openalex.org/works/W7130392796.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2135776491","https://openalex.org/W2149628368","https://openalex.org/W2981087920","https://openalex.org/W4205742757","https://openalex.org/W4247204862","https://openalex.org/W4361994820","https://openalex.org/W4385823130","https://openalex.org/W4388366327","https://openalex.org/W4402112435","https://openalex.org/W7084103406"],"related_works":[],"abstract_inverted_index":{"While":[0],"current":[1],"emotional":[2,89,118],"Text-to-Speech":[3],"(TTS)":[4],"models":[5],"have":[6,28],"successfully":[7],"controlled":[8],"verbal":[9],"prosody,":[10],"they":[11,31],"often":[12,32],"ignore":[13],"non-verbal":[14,26,58],"vocalizations":[15],"(NVs),":[16],"which":[17,37],"are":[18,129],"essential":[19],"for":[20,56,132],"authentic":[21],"human":[22],"emotion.":[23],"Although":[24],"some":[25],"datasets":[27],"recently":[29],"emerged,":[30],"lack":[33],"high-quality,":[34],"fine-grained":[35,57],"annotations,":[36],"restricts":[38],"a":[39,53,73],"model's":[40],"ability":[41],"to":[42,79,92,105],"precisely":[43],"control":[44],"NV":[45,66,81,102,127],"generation.":[46],"To":[47],"address":[48],"this":[49],"limitation,":[50],"we":[51],"propose":[52],"novel":[54],"approach":[55,103],"expression":[59],"synthesis.":[60],"We":[61],"curate":[62],"and":[63,84,86,117,139,143],"reprocess":[64],"female":[65],"utterances":[67],"from":[68],"the":[69],"EARS":[70],"corpus,":[71],"develop":[72],"new":[74],"annotation":[75],"scheme":[76],"using":[77],"tags":[78],"encode":[80],"types,":[82],"frequencies,":[83],"durations,":[85],"build":[87],"an":[88],"TTS":[90],"benchmark":[91],"demonstrate":[93],"its":[94],"effectiveness.":[95],"Our":[96],"evaluation":[97],"shows":[98],"that":[99,126],"while":[100],"our":[101],"leads":[104],"minor":[106],"trade-offs":[107],"in":[108],"perceived":[109],"naturalness,":[110],"it":[111],"significantly":[112],"improves":[113],"expressiveness":[114],"(eMOS":[115],"4.20)":[116],"recognition":[119],"accuracy":[120],"(78.8%).":[121],"Emotion-specific":[122],"analysis":[123],"further":[124],"reveals":[125],"cues":[128],"highly":[130],"effective":[131],"high-arousal":[133],"emotions":[134],"like":[135],"happy":[136],"(82.5":[137],"%)":[138],"fear":[140],"(82.7":[141],"%),":[142],"almost":[144],"perfectly":[145],"convey":[146],"sadness":[147],"(98.3%).":[148]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-19T00:00:00"}