{"id":"https://openalex.org/W4406462025","doi":"https://doi.org/10.1109/slt61566.2024.10832278","title":"Disentangling The Prosody And Semantic Information With Pre-Trained Model For In-Context Learning Based Zero-Shot Voice Conversion","display_name":"Disentangling The Prosody And Semantic Information With Pre-Trained Model For In-Context Learning Based Zero-Shot Voice Conversion","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406462025","doi":"https://doi.org/10.1109/slt61566.2024.10832278"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101416769","display_name":"Zhengyang Chen","orcid":"https://orcid.org/0000-0003-1293-8146"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyang Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695505","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-5653-7195"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432825","display_name":"Mingyang Zhang","orcid":"https://orcid.org/0009-0005-2291-5089"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Zhang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042599889","display_name":"Xuechen Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xuechen Liu","raw_affiliation_strings":["National Institute of Informatics,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"698","last_page":"704"},"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":0.9891999959945679,"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":0.9866999983787537,"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/prosody","display_name":"Prosody","score":0.8086729049682617},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6803880929946899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6776849031448364},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6562960743904114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5791209936141968},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45981085300445557},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.43415483832359314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42960673570632935},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.41152146458625793},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16934078931808472}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8086729049682617},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6803880929946899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6776849031448364},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6562960743904114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5791209936141968},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45981085300445557},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.43415483832359314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42960673570632935},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.41152146458625793},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16934078931808472},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G653225240","display_name":"Privacy and fairness-aware speech dataset generation","funder_award_id":"24K21324","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2518172956","https://openalex.org/W2972359262","https://openalex.org/W2973190269","https://openalex.org/W3015805741","https://openalex.org/W3015826515","https://openalex.org/W3024869864","https://openalex.org/W3036601975","https://openalex.org/W3094635600","https://openalex.org/W3140429000","https://openalex.org/W3161627112","https://openalex.org/W3206189675","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4205742757","https://openalex.org/W4226132755","https://openalex.org/W4252812408","https://openalex.org/W4301371414","https://openalex.org/W4313679638","https://openalex.org/W4372337821","https://openalex.org/W4372340947","https://openalex.org/W4375869015","https://openalex.org/W4375869253","https://openalex.org/W4379259581","https://openalex.org/W4385245566","https://openalex.org/W4385822745","https://openalex.org/W4385823191","https://openalex.org/W4387322685","https://openalex.org/W4392737116","https://openalex.org/W4392902656","https://openalex.org/W4392909760","https://openalex.org/W4392979802","https://openalex.org/W4393147067","https://openalex.org/W4399425629","https://openalex.org/W4401980889","https://openalex.org/W4402301063","https://openalex.org/W4402669711","https://openalex.org/W6762533536","https://openalex.org/W6780218876","https://openalex.org/W6803547063","https://openalex.org/W6805710207","https://openalex.org/W6810447587","https://openalex.org/W6846539466","https://openalex.org/W6848735303","https://openalex.org/W6853165267","https://openalex.org/W6857084855","https://openalex.org/W6862435102","https://openalex.org/W6869301554"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2355553914","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W149862513","https://openalex.org/W2347684782","https://openalex.org/W187117048"],"abstract_inverted_index":{"Voice":[0],"conversion":[1],"(VC)":[2],"aims":[3],"to":[4,100,146],"modify":[5],"the":[6,17,80,105,112,115,143,154],"speaker\u2019s":[7],"timbre":[8,47],"while":[9],"retaining":[10],"speech":[11,27,149],"content.":[12],"Previous":[13],"approaches":[14],"have":[15],"tokenized":[16],"outputs":[18],"from":[19,128],"self-supervised":[20],"into":[21,134],"semantic":[22,75],"tokens,":[23,76],"facilitating":[24],"disentanglement":[25],"of":[26,114,138],"content":[28],"information.":[29],"Recently,":[30],"in-context":[31],"learning":[32],"(ICL)":[33],"has":[34],"emerged":[35],"in":[36,110],"text-to-speech":[37],"(TTS)":[38],"systems":[39],"for":[40],"effectively":[41],"modeling":[42],"specific":[43],"characteristics":[44],"such":[45],"as":[46,151],"through":[48],"context":[49],"conditioning.":[50],"This":[51],"paper":[52],"proposes":[53],"an":[54],"ICL":[55],"capability":[56,145],"enhanced":[57],"VC":[58],"system":[59,107],"(ICL-VC)":[60],"employing":[61],"a":[62,95,129],"mask":[63],"and":[64],"reconstruction":[65],"training":[66],"strategy":[67],"based":[68],"on":[69,79,153],"flow-matching":[70],"generative":[71],"models.":[72,103],"Augmented":[73],"with":[74],"our":[77,135],"experiments":[78],"LibriTTS":[81],"dataset":[82],"demonstrate":[83],"that":[84,92],"ICL-VC":[85,106],"improves":[86],"speaker":[87],"similarity.":[88],"Additionally,":[89],"we":[90,122],"find":[91],"k-means":[93],"is":[94],"versatile":[96],"tokenization":[97],"method":[98],"applicable":[99],"various":[101],"pre-trained":[102,130],"However,":[104],"faces":[108],"challenges":[109],"preserving":[111],"prosody":[113,125,139],"source":[116,148],"speech.":[117],"To":[118],"mitigate":[119],"this":[120],"issue,":[121],"propose":[123],"incorporating":[124],"embeddings":[126,140],"extracted":[127],"emotion":[131],"recognition":[132],"model":[133],"system.":[136],"Integration":[137],"notably":[141],"enhances":[142],"system\u2019s":[144],"preserve":[147],"prosody,":[150],"validated":[152],"Emotional":[155],"Speech":[156],"Database.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}