{"id":"https://openalex.org/W4408345862","doi":"https://doi.org/10.1109/icassp49660.2025.10889012","title":"UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts","display_name":"UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345862","doi":"https://doi.org/10.1109/icassp49660.2025.10889012"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100693030","display_name":"Xiang Li","orcid":"https://orcid.org/0009-0000-1049-4399"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Shenzhen Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058898461","display_name":"Zhi-Qi Cheng","orcid":"https://orcid.org/0000-0002-1720-2085"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhi-Qi Cheng","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026022705","display_name":"Jun-Yan He","orcid":"https://orcid.org/0000-0002-6628-6924"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Jun-Yan He","raw_affiliation_strings":["DAMO Academy,Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAMO Academy,Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031376073","display_name":"Junyao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyao Chen","raw_affiliation_strings":["Shenzhen Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044447422","display_name":"Xiaomao Fan","orcid":"https://orcid.org/0000-0001-8160-1294"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaomao Fan","raw_affiliation_strings":["Shenzhen Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033413473","display_name":"Xiaojiang Peng","orcid":"https://orcid.org/0000-0002-5783-321X"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojiang Peng","raw_affiliation_strings":["Shenzhen Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103099928","display_name":"Alexander G. Hauptmann","orcid":"https://orcid.org/0000-0003-2123-0684"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander G. Hauptmann","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100693030"],"corresponding_institution_ids":["https://openalex.org/I4210152380"],"apc_list":null,"apc_paid":null,"fwci":4.2811,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93240295,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9617999792098999,"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/T12031","display_name":"Speech and dialogue systems","score":0.9617999792098999,"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/computer-science","display_name":"Computer science","score":0.7556272745132446},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5445660352706909},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49383196234703064},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4764295518398285},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37672412395477295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7556272745132446},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5445660352706909},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49383196234703064},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4764295518398285},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37672412395477295}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":40,"referenced_works":["https://openalex.org/W1600722501","https://openalex.org/W2150658333","https://openalex.org/W2738672149","https://openalex.org/W2747874407","https://openalex.org/W2885195348","https://openalex.org/W2962788625","https://openalex.org/W2963609956","https://openalex.org/W2963686995","https://openalex.org/W2964243274","https://openalex.org/W3099284785","https://openalex.org/W3135644023","https://openalex.org/W3163573274","https://openalex.org/W3197034238","https://openalex.org/W4200300291","https://openalex.org/W4221152438","https://openalex.org/W4366493008","https://openalex.org/W4375869257","https://openalex.org/W4375869364","https://openalex.org/W4385245566","https://openalex.org/W4385993826","https://openalex.org/W4391620705","https://openalex.org/W4393152865","https://openalex.org/W4398152753","https://openalex.org/W4403713271","https://openalex.org/W6635084905","https://openalex.org/W6746238782","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6784333009","https://openalex.org/W6787300339","https://openalex.org/W6791353385","https://openalex.org/W6796464841","https://openalex.org/W6796730497","https://openalex.org/W6802591955","https://openalex.org/W6846143095","https://openalex.org/W6847363464","https://openalex.org/W6857178724","https://openalex.org/W6869315008","https://openalex.org/W6911108378"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Emotional":[0,50],"Text-to-Speech":[1,51],"(E-TTS)":[2],"synthesis":[3],"has":[4],"garnered":[5],"significant":[6,142],"attention":[7],"in":[8,144],"recent":[9],"years":[10],"due":[11],"to":[12,15,25,64,98,127],"its":[13],"potential":[14],"revolutionize":[16],"human-computer":[17],"interaction.":[18],"However,":[19],"current":[20],"E-TTS":[21,152],"approaches":[22],"often":[23],"struggle":[24],"capture":[26],"the":[27,46,81,88,119,133],"intricacies":[28],"of":[29,74,77,112],"human":[30],"emotions,":[31],"primarily":[32],"relying":[33],"on":[34,154],"oversimplified":[35],"emotional":[36,59,100,121],"labels":[37],"or":[38],"single-modality":[39],"input.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,166],"introduce":[45],"Unified":[47],"Multimodal":[48],"Prompt-Induced":[49],"System":[52],"(UMETTS),":[53],"a":[54,109],"novel":[55],"framework":[56],"that":[57,130,139],"leverages":[58],"cues":[60],"from":[61],"multiple":[62],"modalities":[63],"generate":[65],"highly":[66],"expressive":[67],"and":[68,87,105,147,157,163],"emotionally":[69],"resonant":[70],"speech.":[71],"The":[72],"core":[73],"UMETTS":[75,140],"consists":[76],"two":[78],"key":[79],"components:":[80],"Emotion":[82,89],"Prompt":[83],"Alignment":[84],"Module":[85],"(EP-Align)":[86],"Embedding-Induced":[90],"TTS":[91,125],"Module(EMI-TTS).":[92],"(1)":[93],"EP-Align":[94],"employs":[95],"contrastive":[96],"learning":[97],"align":[99],"features":[101],"across":[102],"text,":[103],"audio,":[104],"visual":[106],"modalities,":[107],"ensuring":[108],"coherent":[110],"fusion":[111],"multimodal":[113],"information.":[114],"(2)":[115],"Subsequently,":[116],"EMI-TTS":[117],"integrates":[118],"aligned":[120],"embeddings":[122],"with":[123],"state-of-the-art":[124],"models":[126],"synthesize":[128],"speech":[129,148],"accurately":[131],"reflects":[132],"intended":[134],"emotions.":[135],"Extensive":[136],"evaluations":[137],"show":[138],"achieves":[141],"improvements":[143],"emotion":[145],"accuracy":[146],"naturalness,":[149],"outperforming":[150],"traditional":[151],"methods":[153],"both":[155],"objective":[156],"subjective":[158],"metrics.":[159],"To":[160],"facilitate":[161],"reproducibility":[162],"further":[164],"research,":[165],"have":[167],"made":[168],"our":[169],"code":[170],"publicly":[171],"available":[172],"at":[173],"https://github.com/KTTRCDL/UMETTS.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}