{"id":"https://openalex.org/W4416798973","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249309","title":"A Study of Japanese Mixed Emotional Speech Synthesis Based on an End-to-End Emotional Speech Synthesis Model","display_name":"A Study of Japanese Mixed Emotional Speech Synthesis Based on an End-to-End Emotional Speech Synthesis Model","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798973","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249309"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","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/A5120670601","display_name":"Issei Sakata","orcid":null},"institutions":[{"id":"https://openalex.org/I112524849","display_name":"Yamagata University","ror":"https://ror.org/00xy44n04","country_code":"JP","type":"education","lineage":["https://openalex.org/I112524849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Issei Sakata","raw_affiliation_strings":["Graduate School of Science and Engineering, Yamagata University,Yonezawa,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Yamagata University,Yonezawa,Japan","institution_ids":["https://openalex.org/I112524849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112342909","display_name":"Tetsuo Kosaka","orcid":null},"institutions":[{"id":"https://openalex.org/I112524849","display_name":"Yamagata University","ror":"https://ror.org/00xy44n04","country_code":"JP","type":"education","lineage":["https://openalex.org/I112524849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuo Kosaka","raw_affiliation_strings":["Graduate School of Science and Engineering, Yamagata University,Yonezawa,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Yamagata University,Yonezawa,Japan","institution_ids":["https://openalex.org/I112524849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I112524849"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33973829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"789","last_page":"794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9074000120162964,"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":0.9074000120162964,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.02280000038444996,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.01860000006854534,"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/naturalness","display_name":"Naturalness","score":0.8149999976158142},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6068000197410583},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.37619999051094055},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.37130001187324524},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.3391000032424927},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.3336000144481659},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.32989999651908875}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8149999976158142},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6068000197410583},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5839999914169312},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5777000188827515},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3416000008583069},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C3020014160","wikidata":"https://www.wikidata.org/wiki/Q6987190","display_name":"Negative emotion","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.32190001010894775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3151000142097473},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2784999907016754},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.2605000138282776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":15,"referenced_works":["https://openalex.org/W2066064791","https://openalex.org/W2742542661","https://openalex.org/W2964243274","https://openalex.org/W3196225973","https://openalex.org/W3198771897","https://openalex.org/W4297570641","https://openalex.org/W4313316128","https://openalex.org/W4361994820","https://openalex.org/W4385245566","https://openalex.org/W4385822379","https://openalex.org/W4391454536","https://openalex.org/W4395667732","https://openalex.org/W4395681711","https://openalex.org/W4395699642","https://openalex.org/W4406461865"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3,34,57],"examined":[4,94],"mixed":[5,162],"emotion":[6,124,163,175],"speech":[7,15,25,100,138,148,164],"synthesis":[8,16,26,101],"for":[9],"Japanese":[10,65,74],"using":[11],"Emotional-VITS,":[12],"an":[13,23],"emotional":[14,96,109,132,144],"model":[17,61,71],"based":[18],"on":[19,183],"VITS,":[20],"which":[21,167],"is":[22,89],"end-to-end":[24],"model.":[27],"On":[28],"the":[29,51,54,60,70,86,95,105,108,116,128,131,136,140,143,147,150,174,178,184],"dataset":[30],"of":[31,53,107,111,130,142,146,149,170],"pretrained":[32],"models,":[33],"compared":[35],"models":[36,45],"trained":[37,46,62,72],"in":[38,48,64,73,77,99,161,166],"two":[39,168],"languages":[40],"(Japanese":[41],"and":[42,44,75,80,84,102,187],"Chinese)":[43],"only":[47,63],"Japanese.":[49],"Regarding":[50],"quality":[52],"synthesized":[55],"speech,":[56],"confirmed":[58,103],"that":[59,85,104,159,191],"has":[66],"higher":[67,123],"naturalness":[68],"than":[69,115,127],"Chinese":[76],"both":[78],"subjective":[79],"objective":[81],"evaluation":[82],"experiments,":[83],"input":[87],"text":[88],"accurately":[90],"synthesized.":[91,154],"We":[92],"also":[93],"features":[97,110,133,145],"used":[98],"average":[106,129,141],"other":[112,114],"speakers,":[113],"speaker":[117,151],"to":[118,152,194],"be":[119,153],"synthesized,":[120],"yields":[121],"a":[122],"recognition":[125],"rate":[126],"extracted":[134],"from":[135],"target":[137],"or":[139],"Furthermore,":[155],"it":[156,188],"was":[157,189],"found":[158,190],"even":[160],"synthesis,":[165],"types":[169],"emotions":[171,192],"are":[172,197],"mixed,":[173],"recognized":[176],"by":[177],"subject":[179],"changes":[180],"consistently":[181],"depending":[182],"mixing":[185],"ratio,":[186],"close":[193],"human":[195],"sensation":[196],"possible.":[198]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}