{"id":"https://openalex.org/W4319862723","doi":"https://doi.org/10.1109/slt54892.2023.10022433","title":"Exact Prosody Cloning in Zero-Shot Multispeaker Text-to-Speech","display_name":"Exact Prosody Cloning in Zero-Shot Multispeaker Text-to-Speech","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862723","doi":"https://doi.org/10.1109/slt54892.2023.10022433"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022433","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5078880407","display_name":"Florian Lux","orcid":"https://orcid.org/0000-0003-4325-5129"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Florian Lux","raw_affiliation_strings":["University of Stuttgart, Institute for Natural Language Processing,Germany","University of Stuttgart, Institute for Natural Language Processing, Germany"],"affiliations":[{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082226616","display_name":"Julia Koch","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julia Koch","raw_affiliation_strings":["University of Stuttgart, Institute for Natural Language Processing,Germany","University of Stuttgart, Institute for Natural Language Processing, Germany"],"affiliations":[{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020700841","display_name":"Ngoc Thang Vu","orcid":"https://orcid.org/0000-0001-7893-9147"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ngoc Thang Vu","raw_affiliation_strings":["University of Stuttgart, Institute for Natural Language Processing,Germany","University of Stuttgart, Institute for Natural Language Processing, Germany"],"affiliations":[{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing,Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"University of Stuttgart, Institute for Natural Language Processing, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078880407"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":1.1311,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.78184631,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"962","last_page":"969"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9994000196456909,"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":0.9976000189781189,"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":0.9361349940299988},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8388158082962036},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7326911687850952},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7265235781669617},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.627835750579834},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48706749081611633},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.47049474716186523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4555656909942627},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.4177049398422241},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07918709516525269}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9361349940299988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8388158082962036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7326911687850952},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7265235781669617},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.627835750579834},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48706749081611633},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.47049474716186523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4555656909942627},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.4177049398422241},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07918709516525269},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022433","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1875231349","https://openalex.org/W2107860279","https://openalex.org/W2127141656","https://openalex.org/W2130086727","https://openalex.org/W2150769028","https://openalex.org/W2187089797","https://openalex.org/W2527729766","https://openalex.org/W2592497314","https://openalex.org/W2726515241","https://openalex.org/W2788357188","https://openalex.org/W2807627734","https://openalex.org/W2808631503","https://openalex.org/W2808706139","https://openalex.org/W2946200149","https://openalex.org/W2968021853","https://openalex.org/W2972359262","https://openalex.org/W2972802841","https://openalex.org/W2972818416","https://openalex.org/W2973158936","https://openalex.org/W2974194285","https://openalex.org/W2981087920","https://openalex.org/W3007328579","https://openalex.org/W3015826515","https://openalex.org/W3016160783","https://openalex.org/W3024144824","https://openalex.org/W3024869864","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3034949308","https://openalex.org/W3092028330","https://openalex.org/W3095199334","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3097892637","https://openalex.org/W3101882441","https://openalex.org/W3167533889","https://openalex.org/W3196584150","https://openalex.org/W3196843885","https://openalex.org/W3198020407","https://openalex.org/W3198730944","https://openalex.org/W3204379680","https://openalex.org/W3206375275","https://openalex.org/W3210086643","https://openalex.org/W4210970267","https://openalex.org/W4285189120","https://openalex.org/W4296069300","https://openalex.org/W4387941731","https://openalex.org/W4395962180","https://openalex.org/W6604828220","https://openalex.org/W6639350448","https://openalex.org/W6677973343","https://openalex.org/W6748588790","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6763832098","https://openalex.org/W6767005581","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6802659129"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2562096895","https://openalex.org/W2333799855","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W4214652783","https://openalex.org/W258725851"],"abstract_inverted_index":{"The":[0],"cloning":[1],"of":[2,13,17,28,93,101,129],"a":[3,29,66,94,102],"speaker's":[4],"voice":[5,92,117],"using":[6],"an":[7,58],"untranscribed":[8],"reference":[9,31,104],"sample":[10],"is":[11,87],"one":[12],"the":[14,26,48,91,99],"great":[15],"advances":[16],"modern":[18],"neural":[19],"text-to-speech":[20],"(TTS)":[21],"methods.":[22],"Approaches":[23],"for":[24,47,69],"mimicking":[25],"prosody":[27,100],"transcribed":[30],"audio":[32],"have":[33],"also":[34],"been":[35],"proposed":[36],"recently.":[37],"In":[38],"this":[39],"work,":[40],"we":[41],"bring":[42],"these":[43],"two":[44],"tasks":[45],"together":[46],"first":[49],"time":[50],"through":[51],"utterance":[52,59],"level":[53,60],"normalization":[54],"in":[55,109],"conjunction":[56],"with":[57],"speaker":[61,95],"embedding.":[62],"We":[63,83],"further":[64],"introduce":[65],"lightweight":[67],"aligner":[68],"extracting":[70],"fine-grained":[71],"prosodic":[72],"features,":[73],"that":[74,85],"can":[75],"be":[76],"finetuned":[77],"on":[78],"individual":[79],"samples":[80],"within":[81],"seconds.":[82],"show":[84],"it":[86],"possible":[88],"to":[89,114],"clone":[90],"as":[96,98,120],"well":[97],"spoken":[103],"independently":[105],"without":[106],"any":[107],"degradation":[108],"quality":[110],"and":[111,118,124,132,139],"high":[112],"similarity":[113],"both":[115],"original":[116],"prosody,":[119],"our":[121,130],"objective":[122],"evaluation":[123],"human":[125],"study":[126],"show.":[127],"All":[128],"code":[131],"trained":[133],"models":[134],"are":[135],"available,":[136],"alongside":[137],"static":[138],"interactive":[140],"demos.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}