{"id":"https://openalex.org/W4386536205","doi":"https://doi.org/10.1109/taslp.2023.3313413","title":"DiCLET-TTS: Diffusion Model Based Cross-Lingual Emotion Transfer for Text-to-Speech \u2014 A Study Between English and Mandarin","display_name":"DiCLET-TTS: Diffusion Model Based Cross-Lingual Emotion Transfer for Text-to-Speech \u2014 A Study Between English and Mandarin","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386536205","doi":"https://doi.org/10.1109/taslp.2023.3313413"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3313413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3313413","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","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":"https://openalex.org/A5055592507","display_name":"Tao Li","orcid":"https://orcid.org/0000-0001-5578-3960"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Li","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0001-5578-3960","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017581594","display_name":"Chenxu Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxu Hu","raw_affiliation_strings":["Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064364353","display_name":"Jian Cong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Cong","raw_affiliation_strings":["Speech, Audio, and Music Intelligence Group, ByteDance, Shanghai, China","Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio, and Music Intelligence Group, ByteDance, Shanghai, China","institution_ids":["https://openalex.org/I4210145386"]},{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883211","display_name":"Xinfa Zhu","orcid":"https://orcid.org/0000-0001-9275-523X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinfa Zhu","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047338075","display_name":"Jingbei Li","orcid":"https://orcid.org/0000-0002-6284-5979"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingbei Li","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6284-5979","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103162279","display_name":"Qiao Tian","orcid":"https://orcid.org/0000-0002-4078-1273"},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiao Tian","raw_affiliation_strings":["Speech, Audio, and Music Intelligence Group, ByteDance, Shanghai, China","Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio, and Music Intelligence Group, ByteDance, Shanghai, China","institution_ids":["https://openalex.org/I4210145386"]},{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339126","display_name":"Yuping Wang","orcid":"https://orcid.org/0000-0003-2488-5248"},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuping Wang","raw_affiliation_strings":["Speech, Audio, and Music Intelligence Group, ByteDance, Shanghai, China","Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio, and Music Intelligence Group, ByteDance, Shanghai, China","institution_ids":["https://openalex.org/I4210145386"]},{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0001-8234-0823","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2345,"currency":"USD","value_usd":2345},"apc_paid":null,"fwci":2.7563,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92054743,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"3418","last_page":"3430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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/T10860","display_name":"Speech and Audio Processing","score":0.9958000183105469,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.6892387866973877},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6412541270256042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6319172978401184},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6301454305648804},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5033642649650574},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4835922122001648},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.347942054271698},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2577955722808838},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.12577933073043823}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.6892387866973877},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6412541270256042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6319172978401184},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6301454305648804},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5033642649650574},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4835922122001648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.347942054271698},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2577955722808838},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.12577933073043823},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3313413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3313413","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W182973811","https://openalex.org/W1901129140","https://openalex.org/W2092386438","https://openalex.org/W2187089797","https://openalex.org/W2619368999","https://openalex.org/W2748238740","https://openalex.org/W2904459034","https://openalex.org/W2932022923","https://openalex.org/W2963609956","https://openalex.org/W2964002616","https://openalex.org/W2964243274","https://openalex.org/W2968201928","https://openalex.org/W2972473628","https://openalex.org/W2973084242","https://openalex.org/W2979510982","https://openalex.org/W3016139610","https://openalex.org/W3022876224","https://openalex.org/W3024869864","https://openalex.org/W3094785744","https://openalex.org/W3095012670","https://openalex.org/W3095537162","https://openalex.org/W3096514088","https://openalex.org/W3096894480","https://openalex.org/W3097032879","https://openalex.org/W3097777922","https://openalex.org/W3131166446","https://openalex.org/W3135644023","https://openalex.org/W3158762648","https://openalex.org/W3161436426","https://openalex.org/W3168542456","https://openalex.org/W3195366750","https://openalex.org/W3197186640","https://openalex.org/W3197668461","https://openalex.org/W3198032048","https://openalex.org/W3198213150","https://openalex.org/W3198769980","https://openalex.org/W3205369601","https://openalex.org/W4210433094","https://openalex.org/W4214527475","https://openalex.org/W4221153051","https://openalex.org/W4224931727","https://openalex.org/W4226421465","https://openalex.org/W4281739498","https://openalex.org/W4283009359","https://openalex.org/W4283832640","https://openalex.org/W4285405598","https://openalex.org/W4285605725","https://openalex.org/W4304099317","https://openalex.org/W4312933868","https://openalex.org/W4319586674","https://openalex.org/W4320459320","https://openalex.org/W4366493008","https://openalex.org/W4367359628","https://openalex.org/W4395957972","https://openalex.org/W6607506187","https://openalex.org/W6679045638","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6760861152","https://openalex.org/W6763832098","https://openalex.org/W6783713337","https://openalex.org/W6783867762","https://openalex.org/W6786375611","https://openalex.org/W6790220310","https://openalex.org/W6795261426","https://openalex.org/W6795288823","https://openalex.org/W6802527329","https://openalex.org/W6803063772","https://openalex.org/W6803425590","https://openalex.org/W6809940947","https://openalex.org/W6838844135","https://openalex.org/W6840257003","https://openalex.org/W6849953009","https://openalex.org/W6849956205"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W2064370490","https://openalex.org/W172797710","https://openalex.org/W3166813893","https://openalex.org/W2910013580","https://openalex.org/W3165080709","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W2391900574","https://openalex.org/W2909357361"],"abstract_inverted_index":{"While":[0],"the":[1,21,67,76,82,85,89,108,116,141,155,159,162,165,182,191],"performance":[2],"of":[3,88,158,184,194],"cross-lingual":[4,16,31,70],"TTS":[5],"based":[6,53,132],"on":[7],"monolingual":[8],"corpora":[9],"has":[10],"been":[11],"significantly":[12],"improved":[13],"recently,":[14],"generating":[15],"speech":[17,42,175],"still":[18],"suffers":[19],"from":[20,62],"foreign":[22,77],"accent":[23,78],"problem,":[24],"leading":[25],"to":[26,66,74,139,153,169],"limited":[27],"naturalness.":[28],"Besides,":[29],"current":[30],"methods":[32],"ignore":[33],"modeling":[34,156],"emotion,":[35],"which":[36],"is":[37,93,137,151],"indispensable":[38],"paralinguistic":[39],"information":[40],"in":[41,125,164,174,196],"delivery.":[43,176],"In":[44],"this":[45],"paper,":[46],"we":[47],"propose":[48],"DiCLET-TTS,":[49],"a":[50,63,96,103,112,128,147],"Diffusion":[51],"model":[52],"Cross-Lingual":[54],"Emotion":[55],"Transfer":[56],"method":[57],"that":[58],"can":[59],"transfer":[60,179],"emotion":[61,83,109,126,133,163,172,178],"source":[64],"speaker":[65,123,160],"intra-":[68],"and":[69,161,190],"target":[71],"speakers.":[72],"Specifically,":[73],"relieve":[75],"problem":[79,120],"while":[80],"improving":[81],"expressiveness,":[84],"terminal":[86],"distribution":[87],"forward":[90],"diffusion":[91,167],"process":[92,168],"parameterized":[94],"into":[95],"speaker-irrelevant":[97,142,198],"but":[98,143,199],"emotion-related":[99],"linguistic":[100],"prior":[101,104],"by":[102,122],"text":[105],"encoder":[106],"with":[107],"embedding":[110],"as":[111],"condition.":[113],"To":[114],"address":[115],"weaker":[117],"emotional":[118],"expressiveness":[119,173],"caused":[121],"disentanglement":[124],"embedding,":[127],"novel":[129],"orthogonal":[130],"projection":[131],"disentangling":[134],"module":[135],"(OP-EDM)":[136],"proposed":[138],"learn":[140],"emotion-discriminative":[144,200],"embedding.":[145,201],"Moreover,":[146],"condition-enhanced":[148],"DPM":[149],"decoder":[150],"introduced":[152],"strengthen":[154],"ability":[157],"reverse":[166],"further":[170],"improve":[171],"Cross-lingual":[177],"experiments":[180],"show":[181],"superiority":[183],"DiCLET-TTS":[185],"over":[186],"various":[187],"competitive":[188],"models":[189],"good":[192],"design":[193],"OP-EDM":[195],"learning":[197]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}
