{"id":"https://openalex.org/W4415540902","doi":"https://doi.org/10.1145/3746027.3754829","title":"EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting","display_name":"EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540902","doi":"https://doi.org/10.1145/3746027.3754829"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754829","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5111310847","display_name":"Guanrou Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guanrou Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-3614-1346","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chen Yang","orcid":"https://orcid.org/0009-0004-7972-5457"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-7972-5457","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428431","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0001-6939-7438"},"institutions":[{"id":"https://openalex.org/I4210097783","display_name":"Tongde Hospital of Zhejiang Province","ror":"https://ror.org/00trnhw76","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210097783"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":["Tongyi Speech Lab, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6939-7438","affiliations":[{"raw_affiliation_string":"Tongyi Speech Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210097783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101838736","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-8195-3262"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8195-3262","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenxi Chen","orcid":"https://orcid.org/0009-0005-8303-930X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxi Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-8303-930X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396375","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-0356-1968"},"institutions":[{"id":"https://openalex.org/I4210159707","display_name":"Real-Time Innovations (United States)","ror":"https://ror.org/053y5js51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210159707"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Tongyi Speech Lab, Sunnyvale, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0356-1968","affiliations":[{"raw_affiliation_string":"Tongyi Speech Lab, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210159707"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106558173","display_name":"Tianrui Wang","orcid":"https://orcid.org/0000-0002-2765-5889"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrui Wang","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-2765-5889","affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115596565","display_name":"Yifan Yang","orcid":"https://orcid.org/0009-0003-0588-1812"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-0588-1812","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109531461","display_name":"Zhikang Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhikang Niu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-1880-7434","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059916277","display_name":"W P Liu","orcid":"https://orcid.org/0009-0000-5940-5369"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenrui Liu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-5940-5369","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fan Yu","orcid":"https://orcid.org/0009-0005-5958-1131"},"institutions":[{"id":"https://openalex.org/I4210097783","display_name":"Tongde Hospital of Zhejiang Province","ror":"https://ror.org/00trnhw76","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210097783"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yu","raw_affiliation_strings":["Tongyi Speech Lab, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-5958-1131","affiliations":[{"raw_affiliation_string":"Tongyi Speech Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210097783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001133136","display_name":"Zhihao Du","orcid":"https://orcid.org/0000-0003-3509-9322"},"institutions":[{"id":"https://openalex.org/I1294606314","display_name":"Beijing Tongren Hospital","ror":"https://ror.org/013e4n276","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294606314"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Du","raw_affiliation_strings":["Tongyi Speech Lab, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3509-9322","affiliations":[{"raw_affiliation_string":"Tongyi Speech Lab, Beijing, China","institution_ids":["https://openalex.org/I1294606314"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024223042","display_name":"Zhifu Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097783","display_name":"Tongde Hospital of Zhejiang Province","ror":"https://ror.org/00trnhw76","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210097783"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifu Gao","raw_affiliation_strings":["Tongyi Speech Lab, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-5691-7324","affiliations":[{"raw_affiliation_string":"Tongyi Speech Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210097783"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0003-1718-3686"},"institutions":[{"id":"https://openalex.org/I4210097783","display_name":"Tongde Hospital of Zhejiang Province","ror":"https://ror.org/00trnhw76","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210097783"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["Tongyi Speech Lab, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1718-3686","affiliations":[{"raw_affiliation_string":"Tongyi Speech Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210097783"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai Innovation Institute, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7423-617X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai Innovation Institute, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":15,"corresponding_author_ids":["https://openalex.org/A5111310847"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":14.9639,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98773527,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"10748","last_page":"10757"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.567300021648407,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.567300021648407,"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/T12488","display_name":"Mental Health via Writing","score":0.5332000255584717,"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/T10028","display_name":"Topic Modeling","score":0.4900999963283539,"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/set","display_name":"Set (abstract data type)","score":0.6284999847412109},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5354999899864197},{"id":"https://openalex.org/keywords/emotion-perception","display_name":"Emotion perception","score":0.5289000272750854},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.49129998683929443},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.47099998593330383},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4580000042915344},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.44769999384880066},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4424999952316284},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4300000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6541000008583069},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6284999847412109},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5354999899864197},{"id":"https://openalex.org/C2776141551","wikidata":"https://www.wikidata.org/wiki/Q16000087","display_name":"Emotion perception","level":3,"score":0.5289000272750854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5083000063896179},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.49129998683929443},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.47099998593330383},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46129998564720154},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.44769999384880066},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4300000071525574},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4000999927520752},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.37119999527931213},{"id":"https://openalex.org/C2778143943","wikidata":"https://www.wikidata.org/wiki/Q523747","display_name":"Expressed emotion","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33180001378059387},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.28209999203681946},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754829","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W4200300291","https://openalex.org/W4412888872"],"related_works":[],"abstract_inverted_index":{"Human":[0],"speech":[1,109],"goes":[2],"beyond":[3],"the":[4,35,39,75,123,135,147],"mere":[5],"transfer":[6],"of":[7,14,149],"information;":[8],"it":[9],"is":[10],"a":[11,17,48,68,101],"profound":[12],"exchange":[13],"emotions":[15],"and":[16,67,80,93,110,133,154,161,168,177],"connection":[18],"between":[19],"individuals.":[20],"While":[21],"Text-to-Speech":[22],"(TTS)":[23],"models":[24,57],"have":[25],"made":[26],"huge":[27],"progress,":[28],"they":[29],"still":[30],"face":[31],"challenges":[32],"in":[33,38,83],"controlling":[34],"emotional":[36,172],"expression":[37],"generated":[40],"speech.":[41,173],"In":[42],"this":[43],"work,":[44],"we":[45,98],"propose":[46],"EmoVoice,":[47],"novel":[49],"emotion-controllable":[50],"TTS":[51],"model":[52,76],"that":[53,73],"exploits":[54],"large":[55],"language":[56,64,116],"(LLMs)":[58],"to":[59,85,170],"enable":[60],"fine-grained":[61,111],"freestyle":[62],"natural":[63,115],"emotion":[65,105,112,151],"control,":[66],"phoneme":[69,78],"boost":[70],"variant":[71],"design":[72],"makes":[74],"output":[77],"tokens":[79,82],"audio":[81],"parallel":[84],"enhance":[86],"content":[87],"consistency,":[88],"inspired":[89],"by":[90],"chain-of-thought":[91],"(CoT)":[92],"modality-of-thought":[94],"(CoM)":[95],"techniques.":[96],"Besides,":[97],"introduce":[99],"EmoVoice-DB,":[100],"high-quality":[102],"40-hour":[103],"English":[104,124],"dataset":[106],"featuring":[107],"expressive":[108],"labels":[113],"with":[114,157],"descriptions.":[117],"EmoVoice":[118],"achieves":[119],"state-of-the-art":[120],"performance":[121],"on":[122,134],"EmoVoice-DB":[125],"test":[126,138],"set":[127,139],"using":[128,140,163],"only":[129],"synthetic":[130],"training":[131],"data,":[132],"Chinese":[136],"Secap":[137],"our":[141],"in-house":[142],"data.":[143],"We":[144],"further":[145],"investigate":[146],"reliability":[148],"existing":[150],"evaluation":[152],"metrics":[153],"their":[155],"alignment":[156],"human":[158],"perceptual":[159],"preferences,":[160],"explore":[162],"SOTA":[164],"multimodal":[165],"LLMs":[166],"GPT-4o-audio":[167],"Gemini":[169],"assess":[171],"Dataset,":[174],"code,":[175],"checkpoints":[176],"demo":[178],"samples":[179],"are":[180],"available":[181],"at":[182],"https://github.com/yanghaha0908/EmoVoice.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-25T00:00:00"}