{"id":"https://openalex.org/W4408345780","doi":"https://doi.org/10.1109/icassp49660.2025.10889084","title":"Enhancing Zero-Shot Emotional Voice Conversion via Speaker Adaptation and Duration Prediction","display_name":"Enhancing Zero-Shot Emotional Voice Conversion via Speaker Adaptation and Duration Prediction","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345780","doi":"https://doi.org/10.1109/icassp49660.2025.10889084"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889084","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/A5101511218","display_name":"Shiyan Wang","orcid":"https://orcid.org/0000-0002-7873-1984"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shiyan Wang","raw_affiliation_strings":["Key Laboratory of Child Development and Learning Science (Southeast University),Ministry of Education,Nanjing,China,210096"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science (Southeast University),Ministry of Education,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040782290","display_name":"Tianhua Qi","orcid":"https://orcid.org/0009-0005-5780-9374"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhua Qi","raw_affiliation_strings":["Key Laboratory of Child Development and Learning Science (Southeast University),Ministry of Education,Nanjing,China,210096"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science (Southeast University),Ministry of Education,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054796879","display_name":"Cheng Lu","orcid":"https://orcid.org/0000-0002-1477-1020"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Lu","raw_affiliation_strings":["Key Laboratory of Child Development and Learning Science (Southeast University),Ministry of Education,Nanjing,China,210096"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science (Southeast University),Ministry of Education,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077713342","display_name":"Zhaojie Luo","orcid":"https://orcid.org/0000-0002-4173-6319"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaojie Luo","raw_affiliation_strings":["Key Laboratory of Child Development and Learning Science (Southeast University),Ministry of Education,Nanjing,China,210096"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science (Southeast University),Ministry of Education,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029771864","display_name":"Wenming Zheng","orcid":"https://orcid.org/0000-0002-7764-5179"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenming Zheng","raw_affiliation_strings":["Key Laboratory of Child Development and Learning Science (Southeast University),Ministry of Education,Nanjing,China,210096"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science (Southeast University),Ministry of Education,Nanjing,China,210096","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101511218"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":7.2362,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96202569,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.995199978351593,"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":0.995199978351593,"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":0.9916999936103821,"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/duration","display_name":"Duration (music)","score":0.6940690279006958},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.666888415813446},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6193289756774902},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6068570613861084},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5923566818237305},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.47189435362815857},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4263472557067871},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18088281154632568},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11373993754386902},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05824488401412964},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.058221518993377686}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.6940690279006958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.666888415813446},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6193289756774902},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6068570613861084},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5923566818237305},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.47189435362815857},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4263472557067871},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18088281154632568},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11373993754386902},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05824488401412964},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.058221518993377686},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889084","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":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1976725440","https://openalex.org/W2919171658","https://openalex.org/W2938833595","https://openalex.org/W3015241559","https://openalex.org/W3015699566","https://openalex.org/W3015719316","https://openalex.org/W3081192838","https://openalex.org/W3083423753","https://openalex.org/W3127686677","https://openalex.org/W3163573274","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221147462","https://openalex.org/W4285414384","https://openalex.org/W4296069352","https://openalex.org/W4306729455","https://openalex.org/W4372260053","https://openalex.org/W4372260157","https://openalex.org/W4385574033","https://openalex.org/W4385822407","https://openalex.org/W4385823370","https://openalex.org/W4389524060","https://openalex.org/W4391021757","https://openalex.org/W4392904630","https://openalex.org/W4392910613","https://openalex.org/W4402111363","https://openalex.org/W4402669711","https://openalex.org/W6772349387","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6790356757","https://openalex.org/W6796464841","https://openalex.org/W6805710207"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2348837382","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W746329893","https://openalex.org/W2366718574","https://openalex.org/W4205872570"],"abstract_inverted_index":{"Zero-shot":[0],"Emotional":[1],"Voice":[2,74],"Conversion":[3,75],"(EVC)":[4],"aims":[5],"to":[6,12,124,146,151],"transform":[7],"a":[8,14,101,113,117,139],"speaker\u2019s":[9],"emotional":[10,57,97,126,136,152,173],"state":[11],"match":[13],"target":[15,96],"emotion,":[16],"even":[17],"for":[18,82,175],"speakers":[19],"and":[20,52,85,107,135,165,178],"emotion":[21,119],"categories":[22],"that":[23,105],"were":[24],"not":[25],"encountered":[26],"during":[27],"training,":[28],"thereby":[29],"enhancing":[30,131],"the":[31,41,54,61,71,95],"generalization":[32],"ability":[33],"of":[34,56,63,163],"traditional":[35],"EVC":[36],"systems.":[37],"Despite":[38],"advancements":[39],"in":[40,48,60,92,161,168],"field,":[42],"existing":[43],"methods":[44],"often":[45],"face":[46],"challenges":[47],"preserving":[49],"speaker":[50,83,149,166],"identity":[51],"ensuring":[53],"naturalness":[55,164],"expression,":[58],"particularly":[59],"context":[62],"rhythm":[64,91],"modeling.":[65],"To":[66,88],"this":[67],"end,":[68],"we":[69,99],"propose":[70],"Zero-Shot":[72],"Emotion":[73],"(ZSEVC)":[76],"model,":[77],"which":[78],"leverages":[79],"self-supervised":[80],"learning":[81],"adaptation":[84],"duration":[86],"prediction.":[87],"adjust":[89],"speech":[90,110],"alignment":[93],"with":[94,128],"state,":[98],"introduce":[100],"rhythm-aware":[102],"content":[103,129],"encoder":[104],"captures":[106],"refines":[108],"discrete":[109],"units":[111],"at":[112,184],"finer":[114],"granularity.":[115],"Additionally,":[116],"hierarchical":[118],"fusion":[120,142],"scheme":[121],"is":[122,144],"employed":[123],"integrate":[125],"features":[127],"features,":[130],"both":[132],"pronunciation":[133],"accuracy":[134],"expressiveness.":[137],"Moreover,":[138],"residual":[140],"speaker-emotion":[141],"module":[143],"incorporated":[145],"better":[147],"adapt":[148],"characteristics":[150],"prosodic":[153],"variation.":[154],"Experimental":[155],"results":[156],"show":[157],"ZSEVC\u2019s":[158],"superior":[159],"performance":[160],"terms":[162],"similarity":[167],"zero-shot":[169],"scenario,":[170],"successfully":[171],"generating":[172],"speeches":[174],"unseen":[176],"emotions":[177],"speakers.":[179],"Speech":[180],"samples":[181],"are":[182],"available":[183],"https://wosyoo.github.io/ZSEVC.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
