{"id":"https://openalex.org/W4319862431","doi":"https://doi.org/10.1109/slt54892.2023.10022498","title":"Styletts-VC: One-Shot Voice Conversion by Knowledge Transfer From Style-Based TTS Models","display_name":"Styletts-VC: One-Shot Voice Conversion by Knowledge Transfer From Style-Based TTS Models","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862431","doi":"https://doi.org/10.1109/slt54892.2023.10022498","pmid":"https://pubmed.ncbi.nlm.nih.gov/37577031"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022498","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":"conference-paper","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10417535/pdf/nihms-1919646.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023800090","display_name":"Yinghao Aaron Li","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinghao Aaron Li","raw_affiliation_strings":["Columbia University,Department of Electrical Engineering,USA","Department of Electrical Engineering, Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070114472","display_name":"Cong Han","orcid":"https://orcid.org/0000-0003-2121-000X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Han","raw_affiliation_strings":["Columbia University,Department of Electrical Engineering,USA","Department of Electrical Engineering, Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033351155","display_name":"Nima Mesgarani","orcid":"https://orcid.org/0000-0002-2987-759X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nima Mesgarani","raw_affiliation_strings":["Columbia University,Department of Electrical Engineering,USA","Department of Electrical Engineering, Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":2.6724,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.91787502,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"2022","issue":null,"first_page":"920","last_page":"927"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973000288009644,"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":0.9941999912261963,"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/computer-science","display_name":"Computer science","score":0.762120246887207},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6800902485847473},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6627352833747864},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6518242359161377},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5117080211639404},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.46946612000465393},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4378910958766937},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4312141239643097},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4199601411819458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4154098927974701},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10671162605285645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.762120246887207},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6800902485847473},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6627352833747864},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6518242359161377},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5117080211639404},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.46946612000465393},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4378910958766937},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4312141239643097},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4199601411819458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4154098927974701},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10671162605285645},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt54892.2023.10022498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022498","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"},{"id":"pmid:37577031","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37577031","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SLT ... : ... IEEE Workshop on Spoken Language Technology : proceedings. IEEE Workshop on Spoken Language Technology","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10417535","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10417535","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10417535/pdf/nihms-1919646.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SLT Workshop Spok Lang Technol","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:10417535","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10417535","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10417535/pdf/nihms-1919646.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SLT Workshop Spok Lang Technol","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G123412604","display_name":null,"funder_award_id":"R01 DC014279","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G1834331980","display_name":null,"funder_award_id":"R01DC018805","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G5909092158","display_name":null,"funder_award_id":"R01 EB028155","funder_id":"https://openalex.org/F4320337363","funder_display_name":"National Institute of Biomedical Imaging and Bioengineering"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"},{"id":"https://openalex.org/F4320337363","display_name":"National Institute of Biomedical Imaging and Bioengineering","ror":"https://ror.org/00372qc85"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319862431.pdf","grobid_xml":"https://content.openalex.org/works/W4319862431.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2502312327","https://openalex.org/W2603777577","https://openalex.org/W2747070883","https://openalex.org/W2768282280","https://openalex.org/W2932319787","https://openalex.org/W2962780374","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972659941","https://openalex.org/W2998572311","https://openalex.org/W3015209900","https://openalex.org/W3015434413","https://openalex.org/W3015645837","https://openalex.org/W3026874504","https://openalex.org/W3092028330","https://openalex.org/W3095361818","https://openalex.org/W3096864844","https://openalex.org/W3098656025","https://openalex.org/W3154451338","https://openalex.org/W3163475957","https://openalex.org/W3163568691","https://openalex.org/W3196667132","https://openalex.org/W3197659778","https://openalex.org/W3197763626","https://openalex.org/W3208743843","https://openalex.org/W4210282084","https://openalex.org/W4221141917","https://openalex.org/W4225304461","https://openalex.org/W4320451749","https://openalex.org/W6724804524","https://openalex.org/W6761768988","https://openalex.org/W6762533536","https://openalex.org/W6777694618","https://openalex.org/W6783867762","https://openalex.org/W6805710207","https://openalex.org/W6809662130"],"related_works":["https://openalex.org/W2973062255","https://openalex.org/W2405486528","https://openalex.org/W2897924318","https://openalex.org/W3015826515","https://openalex.org/W2030361736","https://openalex.org/W2147551994","https://openalex.org/W2982277844","https://openalex.org/W3011034465","https://openalex.org/W2044525818","https://openalex.org/W3169874602"],"abstract_inverted_index":{"One-shot":[0],"voice":[1,127],"conversion":[2,128],"(VC)":[3],"aims":[4],"to":[5,12,52],"convert":[6],"speech":[7,24,38,55,106],"from":[8,25,60],"any":[9],"source":[10],"speaker":[11,16],"an":[13,87],"arbitrary":[14],"target":[15,27],"with":[17,80],"only":[18],"a":[19,40,49,92],"few":[20],"seconds":[21],"of":[22],"reference":[23],"the":[26,34,71,110,123],"speaker.":[28],"This":[29],"relies":[30],"heavily":[31],"on":[32],"disentangling":[33],"speaker's":[35],"identity":[36],"and":[37,68,83,96,133],"content,":[39],"task":[41],"that":[42,117],"still":[43],"remains":[44],"challenging.":[45],"Here,":[46],"we":[47],"propose":[48],"novel":[50,97],"approach":[51,102,119],"learning":[53,59,86],"disentangled":[54,105],"representation":[56,107],"by":[57],"transfer":[58,95],"style-based":[61,72],"text-to-speech":[62],"(TTS)":[63],"models.":[64],"With":[65],"cycle":[66],"consistent":[67],"adversarial":[69],"training,":[70],"TTS":[73],"models":[74,129],"can":[75,120],"perform":[76],"transcription-guided":[77],"one-shot":[78,126],"VC":[79],"high":[81],"fidelity":[82],"similarity.":[84,134],"By":[85],"additional":[88],"mel-spectrogram":[89],"encoder":[90],"through":[91],"teacher-student":[93],"knowledge":[94],"data":[98],"augmentation":[99],"scheme,":[100],"our":[101,118],"results":[103],"in":[104,130],"without":[108],"needing":[109],"input":[111],"text.":[112],"The":[113],"subjective":[114],"evaluation":[115],"shows":[116],"significantly":[121],"outperform":[122],"previous":[124],"state-of-the-art":[125],"both":[131],"naturalness":[132]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2025-10-10T00:00:00"}
