{"id":"https://openalex.org/W4417090823","doi":"https://doi.org/10.48550/arxiv.2504.12867","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":"2025-04-17","ids":{"openalex":"https://openalex.org/W4417090823","doi":"https://doi.org/10.48550/arxiv.2504.12867"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2504.12867","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.12867","pdf_url":"https://arxiv.org/pdf/2504.12867","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.12867","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111310847","display_name":"Guanrou Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang, Guanrou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350512","display_name":"Yang Chen","orcid":"https://orcid.org/0009-0008-1672-3744"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428431","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0001-6939-7438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101838736","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-8195-3262"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Ziyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034677845","display_name":"Wenxi Chen","orcid":"https://orcid.org/0009-0005-8303-930X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Wenxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396375","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-0356-1968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106558173","display_name":"Tianrui Wang","orcid":"https://orcid.org/0000-0002-2765-5889"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tianrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100743978","display_name":"Yifan Yang","orcid":"https://orcid.org/0000-0003-3313-5473"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109531461","display_name":"Zhikang Niu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niu, Zhikang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059916277","display_name":"W P Liu","orcid":"https://orcid.org/0009-0000-5940-5369"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Wenrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108578966","display_name":"Fan Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001133136","display_name":"Zhihao Du","orcid":"https://orcid.org/0000-0003-3509-9322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Zhihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024223042","display_name":"Zhifu Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Zhifu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101777589","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0001-7795-437X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, ShiLiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":15,"corresponding_author_ids":["https://openalex.org/A5111310847"],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.35350000858306885,"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":0.35350000858306885,"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":0.18080000579357147,"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":0.13420000672340393,"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":0.6258000135421753},{"id":"https://openalex.org/keywords/emotion-perception","display_name":"Emotion perception","score":0.5475000143051147},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5307999849319458},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.48980000615119934},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.46700000762939453},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.45840001106262207},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.44999998807907104},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4415000081062317},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.43479999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6498000025749207},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6258000135421753},{"id":"https://openalex.org/C2776141551","wikidata":"https://www.wikidata.org/wiki/Q16000087","display_name":"Emotion perception","level":3,"score":0.5475000143051147},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5307999849319458},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5153999924659729},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46880000829696655},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.46700000762939453},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40869998931884766},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C2778143943","wikidata":"https://www.wikidata.org/wiki/Q523747","display_name":"Expressed emotion","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.35339999198913574},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3398999869823456},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2504.12867","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.12867","pdf_url":"https://arxiv.org/pdf/2504.12867","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},{"id":"doi:10.48550/arxiv.2504.12867","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.12867","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.12867","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.12867","pdf_url":"https://arxiv.org/pdf/2504.12867","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417090823.pdf","grobid_xml":"https://content.openalex.org/works/W4417090823.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"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],"chain-of-modality":[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":[],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}