{"id":"https://openalex.org/W4409474293","doi":"https://doi.org/10.1109/taffc.2025.3561267","title":"EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech Via Emotion-Adaptive Spherical Vector","display_name":"EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech Via Emotion-Adaptive Spherical Vector","publication_year":2025,"publication_date":"2025-04-15","ids":{"openalex":"https://openalex.org/W4409474293","doi":"https://doi.org/10.1109/taffc.2025.3561267"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2025.3561267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3561267","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Affective Computing","raw_type":"journal-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/A5046627773","display_name":"Deok\u2013Hyeon Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Deok-Hyeon Cho","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea","Department of Artificial Intelligence, Korea University, 145, Anam-ro, Seongbuk-gu, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-4673-9882","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, 145, Anam-ro, Seongbuk-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033088100","display_name":"Hyung-Seok Oh","orcid":"https://orcid.org/0000-0001-7229-8123"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyung-Seok Oh","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea","Department of Artificial Intelligence, Korea University, 145, Anam-ro, Seongbuk-gu, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-7229-8123","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, 145, Anam-ro, Seongbuk-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007493723","display_name":"Seung-Bin Kim","orcid":"https://orcid.org/0000-0002-2287-9111"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-Bin Kim","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea","Department of Artificial Intelligence, Korea University, 145, Anam-ro, Seongbuk-gu, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-2287-9111","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, 145, Anam-ro, Seongbuk-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011014617","display_name":"Seong\u2013Whan Lee","orcid":"https://orcid.org/0000-0002-6249-4996"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong-Whan Lee","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea","Department of Artificial Intelligence, Korea University, 145, Anam-ro, Seongbuk-gu, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-6249-4996","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, 145, Anam-ro, Seongbuk-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":13.5708,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.98571868,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"16","issue":"3","first_page":"2365","last_page":"2380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9409000277519226,"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":0.9409000277519226,"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":0.9203000068664551,"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/zero","display_name":"Zero (linguistics)","score":0.7437558770179749},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5721796154975891},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5570270419120789},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5320497751235962},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4663037061691284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3448094129562378},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.321654736995697},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11057314276695251},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08008274435997009},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06376928091049194}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.7437558770179749},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5721796154975891},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5570270419120789},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5320497751235962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4663037061691284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3448094129562378},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.321654736995697},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11057314276695251},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08008274435997009},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06376928091049194},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taffc.2025.3561267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3561267","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Affective Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W571907995","https://openalex.org/W1731081199","https://openalex.org/W1966797434","https://openalex.org/W2003653478","https://openalex.org/W2043301392","https://openalex.org/W2143969506","https://openalex.org/W2146334809","https://openalex.org/W2149628368","https://openalex.org/W2152194780","https://openalex.org/W2165894799","https://openalex.org/W2294130536","https://openalex.org/W2515074106","https://openalex.org/W2742542661","https://openalex.org/W2793521999","https://openalex.org/W2800822639","https://openalex.org/W2903739847","https://openalex.org/W2938833595","https://openalex.org/W2972359262","https://openalex.org/W2978534460","https://openalex.org/W3008691130","https://openalex.org/W3015645837","https://openalex.org/W3015719316","https://openalex.org/W3015841875","https://openalex.org/W3095701549","https://openalex.org/W3146550708","https://openalex.org/W3195366750","https://openalex.org/W3196543367","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4205742757","https://openalex.org/W4210777104","https://openalex.org/W4214527475","https://openalex.org/W4221147462","https://openalex.org/W4224926192","https://openalex.org/W4226421465","https://openalex.org/W4252812408","https://openalex.org/W4283832640","https://openalex.org/W4296069352","https://openalex.org/W4313316128","https://openalex.org/W4319459137","https://openalex.org/W4361994820","https://openalex.org/W4366493008","https://openalex.org/W4378194758","https://openalex.org/W4390604258","https://openalex.org/W4391776220","https://openalex.org/W4392904615","https://openalex.org/W4392931276","https://openalex.org/W4393994096","https://openalex.org/W4396542467","https://openalex.org/W4399527282","https://openalex.org/W4402111363","https://openalex.org/W4402115961","https://openalex.org/W4402669711","https://openalex.org/W4406461501","https://openalex.org/W4406461672","https://openalex.org/W4406521093"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Emotional":[0],"text-to-speech":[1],"(TTS)":[2],"has":[3],"advanced":[4],"significantly,":[5],"but":[6],"challenges":[7],"persist":[8],"due":[9],"to":[10,101,121],"the":[11,30,123,138,141],"complexity":[12],"of":[13,62,140],"emotions":[14],"and":[15,21,47,72,89,104,133,147,162],"limitations":[16],"in":[17,112,144,155],"emotional":[18,34,48,70,87,157],"speech":[19,35,65],"datasets":[20,36],"models.":[22],"A":[23],"key":[24],"issue":[25],"with":[26,66,92],"previous":[27],"studies":[28],"is":[29],"reliance":[31],"on":[32],"limited":[33],"or":[37],"extensive":[38],"manual":[39,75],"annotations,":[40],"which":[41],"restrict":[42],"generalization":[43,100],"across":[44,159],"different":[45],"speakers":[46,164],"styles.":[49],"To":[50,107],"address":[51],"this,":[52],"we":[53,115,136],"propose":[54],"EmoSphere++,":[55],"an":[56,117],"emotioncontrollable":[57],"zero-shot":[58,113,128],"TTS":[59],"model":[60,143],"capable":[61],"generating":[63],"expressive":[64],"fine-grained":[67],"control":[68],"over":[69],"style":[71,88,96,124,146],"intensity\u2014without":[73],"requiring":[74],"annotations.":[76],"We":[77],"introduce":[78,116],"a":[79,93],"novel":[80],"emotion-adaptive":[81],"spherical":[82],"vector":[83],"that":[84,98],"effectively":[85],"captures":[86],"intensity,":[90],"along":[91],"joint":[94],"attribute":[95],"encoder":[97],"enhances":[99],"both":[102,131,160],"seen":[103,161],"unseen":[105,163],"speakers.":[106],"further":[108],"improve":[109],"emotion":[110,145],"transfer":[111,125],"scenarios,":[114],"additional":[118],"disentanglement":[119],"method":[120],"enhance":[122],"performance":[126],"for":[127],"scenarios.":[129],"Through":[130],"objective":[132],"subjective":[134],"evaluations,":[135],"demonstrate":[137],"benefits":[139],"proposed":[142],"intensity":[148],"modeling,":[149],"as":[150,152],"well":[151],"its":[153],"effectiveness":[154],"enhancing":[156],"expressiveness":[158]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":4}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}