{"id":"https://openalex.org/W4412623335","doi":"https://doi.org/10.1109/lsp.2025.3592588","title":"Emotional Style Transfer With Intensity Control in Zero-Shot TTS","display_name":"Emotional Style Transfer With Intensity Control in Zero-Shot TTS","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412623335","doi":"https://doi.org/10.1109/lsp.2025.3592588"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3592588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3592588","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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":null,"display_name":"Haoyu Wang","orcid":"https://orcid.org/0009-0009-2393-8679"},"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":true,"raw_author_name":"Haoyu Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, China"],"raw_orcid":"https://orcid.org/0009-0009-2393-8679","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028353824","display_name":"Chunyu Qiang","orcid":"https://orcid.org/0009-0007-2290-3074"},"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":"Chunyu Qiang","raw_affiliation_strings":["School of New Media and Communication, Tianjin University, Tianjin, China","Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, China"],"raw_orcid":"https://orcid.org/0009-0007-2290-3074","affiliations":[{"raw_affiliation_string":"School of New Media and Communication, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049261843","display_name":"Tianrui Wang","orcid":"https://orcid.org/0009-0005-1517-9589"},"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 Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cheng Gong","orcid":"https://orcid.org/0009-0004-0272-3541"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Gong","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China","Institute of Artificial Intelligence (TeleAI), China Telecom, China"],"raw_orcid":"https://orcid.org/0009-0004-0272-3541","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]},{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"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":"Longbiao Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, China"],"raw_orcid":"https://orcid.org/0000-0002-8094-6861","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20032765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"3137","last_page":"3141"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9193999767303467,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9193999767303467,"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/shot","display_name":"Shot (pellet)","score":0.53813236951828},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5065006017684937},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4964025616645813},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.4389284551143646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42993980646133423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3387095332145691},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.14567086100578308},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12091219425201416},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09627798199653625}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.53813236951828},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5065006017684937},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4964025616645813},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.4389284551143646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42993980646133423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3387095332145691},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.14567086100578308},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12091219425201416},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09627798199653625},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3592588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3592588","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2883670753","display_name":null,"funder_award_id":"U23B2053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7732325329","display_name":null,"funder_award_id":"62176182","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2752796333","https://openalex.org/W3015805741","https://openalex.org/W3139170550","https://openalex.org/W3151450932","https://openalex.org/W3163573274","https://openalex.org/W3195366750","https://openalex.org/W3197580070","https://openalex.org/W3197668461","https://openalex.org/W3197943112","https://openalex.org/W3209984917","https://openalex.org/W4210433094","https://openalex.org/W4226421465","https://openalex.org/W4294311176","https://openalex.org/W4297841867","https://openalex.org/W4366493008","https://openalex.org/W4372260402","https://openalex.org/W4385822407","https://openalex.org/W4385822745","https://openalex.org/W4390075359","https://openalex.org/W4391620705","https://openalex.org/W4401070302","https://openalex.org/W4402301063","https://openalex.org/W4402301096","https://openalex.org/W4402669711","https://openalex.org/W4405709630","https://openalex.org/W4406461681","https://openalex.org/W4409763016","https://openalex.org/W4412945617","https://openalex.org/W6750489868","https://openalex.org/W6783867762","https://openalex.org/W6802591955","https://openalex.org/W6846143095","https://openalex.org/W6869301554","https://openalex.org/W6870225445"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W4411535265","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,26,40,131,152],"zero-shot":[3],"text-to-speech":[4],"have":[5],"enabled":[6],"the":[7,13,30,126,132,153],"generated":[8],"speech":[9,25,151],"to":[10,46,62,98],"preserve":[11],"both":[12],"speaker's":[14],"identity":[15,85],"and":[16,54,65,86,102,105,147],"emotion,":[17],"guided":[18],"by":[19],"a":[20,37,74,92,106],"reference":[21],"speech.":[22,134],"However,":[23],"generating":[24],"emotional":[27,87,114,129,149,154],"styles":[28],"that":[29,79,112,138],"target":[31],"speaker":[32,53,66,84,118],"has":[33],"never":[34],"exhibited":[35],"remains":[36],"central":[38],"challenge":[39],"style":[41,55,130,155],"transfer.":[42],"Existing":[43],"methods":[44],"attempt":[45],"achieve":[47],"this":[48],"through":[49],"disentangled":[50],"modeling":[51],"of":[52,128],"representations,":[56],"yet":[57],"insufficient":[58],"disentanglement":[59],"often":[60],"leads":[61],"weak":[63],"expressiveness":[64,115],"leakage.":[67],"To":[68],"address":[69],"these":[70],"limitations,":[71],"we":[72,90],"propose":[73],"robust":[75],"LM-based":[76],"TTS":[77],"framework":[78],"enables":[80,122],"fine-grained":[81,100],"control":[82,124],"over":[83,125],"style.":[88],"Specifically,":[89],"introduce":[91],"frame-level":[93],"Style":[94,109],"Transfer":[95],"Pitch":[96],"Predictor":[97],"capture":[99],"prosodic":[101],"speaker-related":[103],"information,":[104],"Speaker":[107],"Emotional":[108],"Alignment":[110],"module":[111],"strengthens":[113],"while":[116],"preserving":[117],"identity.":[119],"Our":[120],"method":[121],"precise":[123],"intensity":[127],"synthesized":[133,150],"Experimental":[135],"results":[136],"demonstrate":[137],"our":[139],"approach":[140],"outperforms":[141],"existing":[142],"methods,":[143],"delivering":[144],"more":[145],"expressive":[146],"controllable":[148],"transfer":[156],"task.":[157],"Audio":[158],"samples":[159],"can":[160],"be":[161],"available":[162],"at":[163],"<uri":[164],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[165],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://whyrrrrun.github.io/ICST.github.io/</uri>.":[166]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
