{"id":"https://openalex.org/W4402301096","doi":"https://doi.org/10.1109/taslp.2024.3453606","title":"U-Style: Cascading U-Nets With Multi-Level Speaker and Style Modeling for Zero-Shot Voice Cloning","display_name":"U-Style: Cascading U-Nets With Multi-Level Speaker and Style Modeling for Zero-Shot Voice Cloning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402301096","doi":"https://doi.org/10.1109/taslp.2024.3453606"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3453606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3453606","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":true,"raw_author_name":"Tao Li","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China"],"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/A5106698700","display_name":"Zhichao Wang","orcid":"https://orcid.org/0000-0001-8075-1784"},"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":"Zhichao Wang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China"],"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/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"],"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/A5064364353","display_name":"Jian Cong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Cong","raw_affiliation_strings":["Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103162279","display_name":"Qiao Tian","orcid":"https://orcid.org/0000-0002-4078-1273"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao Tian","raw_affiliation_strings":["Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339106","display_name":"Yu\u2010Ping Wang","orcid":"https://orcid.org/0000-0001-9340-5864"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuping Wang","raw_affiliation_strings":["Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, Shanghai, China"],"affiliations":[{"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"],"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":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5055592507"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":2.4095,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90316341,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"4026","last_page":"4035"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9973999857902527,"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/T11309","display_name":"Music and Audio Processing","score":0.9937999844551086,"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/style","display_name":"Style (visual arts)","score":0.7071041464805603},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.6073061227798462},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5344703793525696},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5051403641700745},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4641624093055725},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.443963885307312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.39768117666244507},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.30808091163635254},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.2063523530960083},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.0937165915966034},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.05853810906410217},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05325442552566528}],"concepts":[{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.7071041464805603},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.6073061227798462},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5344703793525696},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5051403641700745},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4641624093055725},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.443963885307312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39768117666244507},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30808091163635254},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.2063523530960083},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0937165915966034},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.05853810906410217},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05325442552566528}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3453606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3453606","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W2502312327","https://openalex.org/W2904459034","https://openalex.org/W2932022923","https://openalex.org/W2939913319","https://openalex.org/W2963609956","https://openalex.org/W2972659941","https://openalex.org/W3015645837","https://openalex.org/W3015826515","https://openalex.org/W3022876224","https://openalex.org/W3094785744","https://openalex.org/W3097777922","https://openalex.org/W3135644023","https://openalex.org/W3162794600","https://openalex.org/W3163475957","https://openalex.org/W3163573274","https://openalex.org/W3163654539","https://openalex.org/W3196584150","https://openalex.org/W3200756692","https://openalex.org/W4210433094","https://openalex.org/W4226421465","https://openalex.org/W4283731195","https://openalex.org/W4283832640","https://openalex.org/W4289383906","https://openalex.org/W4294311176","https://openalex.org/W4297841574","https://openalex.org/W4313148337","https://openalex.org/W4313679638","https://openalex.org/W4323651091","https://openalex.org/W4366460484","https://openalex.org/W4372259784","https://openalex.org/W4372260402","https://openalex.org/W4372260509","https://openalex.org/W4384615685","https://openalex.org/W4385823160","https://openalex.org/W4386536205","https://openalex.org/W4395957972","https://openalex.org/W6639480849","https://openalex.org/W6724804524","https://openalex.org/W6745697700","https://openalex.org/W6748588790","https://openalex.org/W6749555683","https://openalex.org/W6755300632","https://openalex.org/W6760861152","https://openalex.org/W6763832098","https://openalex.org/W6783867762","https://openalex.org/W6795261426","https://openalex.org/W6795807602","https://openalex.org/W6803547063","https://openalex.org/W6805710207","https://openalex.org/W6840257003","https://openalex.org/W6846143095","https://openalex.org/W6848735303","https://openalex.org/W6850334629","https://openalex.org/W6851724922","https://openalex.org/W6854199242"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2099333848"],"abstract_inverted_index":{"Zero-shot":[0],"speaker":[1,10,24,44,50,73,82,93,150,157,167,222,227,239,250],"cloning":[2,223],"aims":[3],"to":[4,78,183,203,240],"synthesize":[5],"speech":[6,20,39],"for":[7],"any":[8],"target":[9,49,243],"unseen":[11,156,221,237,242],"during":[12],"TTS":[13],"system":[14],"building,":[15],"given":[16],"only":[17,87],"a":[18,115,121],"single":[19],"reference":[21],"of":[22,69,187,248],"the":[23,33,48,56,66,80,111,127,131,175,185,217,233],"at":[25],"hand.":[26],"Although":[27],"more":[28],"practical":[29],"in":[30,55,200,220,254],"real":[31],"applications,":[32],"current":[34],"zero-shot":[35,57,255],"methods":[36,219],"still":[37],"produce":[38],"with":[40,51],"undesirable":[41],"naturalness":[42,186,225],"and":[43,74,83,94,120,130,144,151,158,168,178,195,207,226,252],"similarity.":[45,228],"Moreover,":[46],"endowing":[47],"arbitrary":[52,92,96],"speaking":[53],"styles":[54],"setup":[58],"has":[59],"not":[60],"been":[61],"considered.":[62],"This":[63],"is":[64,77,139],"because":[65],"unique":[67],"challenge":[68],"<italic":[70,104,116,122],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[71,105,117,123],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">zero-shot":[72],"style":[75,84,152,159,169,196,234,253],"cloning</i>":[76],"learn":[79],"disentangled":[81],"representations":[85],"from":[86,235],"short":[88],"references":[89],"representing":[90],"an":[91,95,236],"style.":[97],"To":[98,154],"address":[99],"this":[100],"challenge,":[101],"we":[102,190],"propose":[103],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">U-Style</i>,":[106],"which":[107],"employs":[108],"Grad-TTS":[109],"as":[110],"backbone,":[112],"particularly":[113],"cascading":[114],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">speaker-specific":[118],"encoder</i>":[119,125],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">style-specific":[124],"between":[126],"text":[128],"encoder":[129],"diffusion":[132],"decoder.":[133],"Thus,":[134],"leveraging":[135],"signal":[136],"perturbation,":[137],"U-Style":[138,214,230],"explicitly":[140],"decomposed":[141],"into":[142],"speaker-":[143],"style-specific":[145],"modeling":[146,160,170],"parts,":[147],"achieving":[148,245],"better":[149],"disentanglement.":[153],"improve":[155,184],"ability,":[161],"these":[162,201],"two":[163],"encoders":[164,202],"conduct":[165],"multi-level":[166],"by":[171],"skip-connected":[172],"U-nets,":[173],"incorporating":[174],"representation":[176,205],"extraction":[177,206],"information":[179],"reconstruction":[180],"process.":[181],"Besides,":[182],"synthetic":[188],"speech,":[189],"adopt":[191],"mean-based":[192],"instance":[193],"normalization":[194,199],"adaptive":[197],"layer":[198],"perform":[204],"condition":[208],"adaptation,":[209],"respectively.":[210],"Experiments":[211],"show":[212],"that":[213],"significantly":[215],"surpasses":[216],"state-of-the-art":[218],"regarding":[224],"Notably,":[229],"can":[231],"transfer":[232],"source":[238],"another":[241],"speaker,":[244],"flexible":[246],"combinations":[247],"desired":[249],"timbre":[251],"voice":[256],"cloning.":[257]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2025-10-10T00:00:00"}
