{"id":"https://openalex.org/W7107866763","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249123","title":"EFTTS: Zero-Shot Emotional Speech Synthesis via Conditional Flow Matching and Self-Supervised Representations","display_name":"EFTTS: Zero-Shot Emotional Speech Synthesis via Conditional Flow Matching and Self-Supervised Representations","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7107866763","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249123"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249123","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":null,"display_name":"Haoyu Wang","orcid":null},"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":"Haoyu Wang","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiale Chen","orcid":null},"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":"Jiale Chen","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiaxun Li","orcid":null},"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":"Jiaxun Li","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sizhe Shan","orcid":null},"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":"Sizhe Shan","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yuehai Wang","orcid":null},"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":"Yuehai Wang","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74551676,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"795","last_page":"800"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9021999835968018,"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":0.9021999835968018,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.024800000712275505,"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/T10028","display_name":"Topic Modeling","score":0.009800000116229057,"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/paralanguage","display_name":"Paralanguage","score":0.7993999719619751},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5648999810218811},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5454999804496765},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4494999945163727},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4203999936580658},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.3497999906539917},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32199999690055847}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.7993999719619751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6474999785423279},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6061000227928162},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5648999810218811},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5454999804496765},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43059998750686646},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4032000005245209},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249123","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":[{"score":0.5152162909507751,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2603777577","https://openalex.org/W3010916717","https://openalex.org/W3015841875","https://openalex.org/W3160329778","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4200300291","https://openalex.org/W4205742757","https://openalex.org/W4221152438","https://openalex.org/W4224926192","https://openalex.org/W4372267432","https://openalex.org/W4375869364","https://openalex.org/W4385822379","https://openalex.org/W4392904491","https://openalex.org/W4392904830","https://openalex.org/W4392931276","https://openalex.org/W4396542467","https://openalex.org/W4402115961"],"related_works":[],"abstract_inverted_index":{"Text-to-speech":[0],"(TTS)":[1],"technology":[2],"has":[3],"made":[4],"significant":[5],"advancements.":[6],"However,":[7],"generating":[8],"high-quality,":[9,117],"controllable":[10,118],"emotional":[11,34,39,64,106,119],"speech":[12,83,120],"remains":[13],"challenging":[14],"due":[15],"to":[16,52,79],"the":[17,89],"complex":[18],"nature":[19],"of":[20,105],"emotions":[21],"and":[22,47,66,92,109],"speaker":[23],"variability.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28,74],"propose":[29],"EFTTS,":[30],"a":[31,42,113],"controllable,":[32],"zero-shot":[33],"TTS":[35],"model.":[36],"EFTTS":[37,99],"extracts":[38],"features":[40,55],"using":[41],"self-supervised":[43],"emotion":[44,54,68,77],"representation":[45],"model":[46,53],"utilizes":[48],"conditional":[49],"flow":[50],"matching":[51],"with":[56,88],"text":[57,91],"inputs.":[58],"This":[59],"approach":[60],"allows":[61],"for":[62,116],"precise":[63],"control":[65],"decouples":[67],"from":[69],"other":[70],"paralinguistic":[71],"features.":[72],"Additionally,":[73],"introduce":[75],"zeroshot":[76],"transfer":[78],"generate":[80],"emotionally":[81],"appropriate":[82],"that":[84,98],"is":[85],"closely":[86],"aligned":[87],"input":[90],"reference":[93],"speech.":[94],"Experimental":[95],"results":[96],"show":[97],"outperforms":[100],"existing":[101],"methods":[102],"in":[103],"terms":[104],"expressiveness,":[107],"naturalness,":[108],"synthesis":[110],"quality,":[111],"offering":[112],"promising":[114],"solution":[115],"synthesis.":[121],"Demo":[122],"samples":[123],"are":[124],"available":[125],"at":[126],"https://bigbroes.github.io/EFTTS/.":[127]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}