{"id":"https://openalex.org/W7148609082","doi":"https://doi.org/10.1109/asru65441.2025.11434735","title":"GenVC: Self-Supervised Zero-Shot Voice Conversion","display_name":"GenVC: Self-Supervised Zero-Shot Voice Conversion","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148609082","doi":"https://doi.org/10.1109/asru65441.2025.11434735"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5076833848","display_name":"Zexin Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zexin Cai","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024403590","display_name":"Henry Li Xinyuan","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henry Li Xinyuan","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109715082","display_name":"Ashi Garg","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashi Garg","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leibny Paola Garc\u00eda-Perera","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070418792","display_name":"Kevin Duh","orcid":"https://orcid.org/0000-0001-8107-4383"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Duh","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132804747","display_name":"Matthew Wiesner","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Wiesner","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111560316","display_name":"Nicholas Andrews","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Andrews","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5076833848"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":2.3568,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93405695,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9409999847412109,"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":0.9409999847412109,"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/T10863","display_name":"Voice and Speech Disorders","score":0.021800000220537186,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.005499999970197678,"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/naturalness","display_name":"Naturalness","score":0.7842000126838684},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7081000208854675},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5406000018119812},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5336999893188477},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5139999985694885},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43070000410079956},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.39739999175071716},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.35830000042915344}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7842000126838684},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7081000208854675},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6837999820709229},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6761000156402588},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5406000018119812},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5336999893188477},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5139999985694885},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43070000410079956},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30390000343322754},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2935999929904938},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C2984865316","wikidata":"https://www.wikidata.org/wiki/Q25481968","display_name":"Speech act","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.404326468706131,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W165114865","https://openalex.org/W1494198834","https://openalex.org/W2726515241","https://openalex.org/W2745644908","https://openalex.org/W2808631503","https://openalex.org/W2972359262","https://openalex.org/W3024869864","https://openalex.org/W3095410713","https://openalex.org/W3097952294","https://openalex.org/W3098557217","https://openalex.org/W3160950295","https://openalex.org/W3197763626","https://openalex.org/W3207300132","https://openalex.org/W3209984917","https://openalex.org/W3213785244","https://openalex.org/W3215615641","https://openalex.org/W4372260053","https://openalex.org/W4372260476","https://openalex.org/W4381786045","https://openalex.org/W4385245566","https://openalex.org/W4386132131","https://openalex.org/W4390075359","https://openalex.org/W4392909842","https://openalex.org/W4401358097","https://openalex.org/W4402112198","https://openalex.org/W4402112533","https://openalex.org/W4402671538","https://openalex.org/W4402672020","https://openalex.org/W4406417959","https://openalex.org/W4406461461","https://openalex.org/W4406461865","https://openalex.org/W4406461995","https://openalex.org/W7133196460","https://openalex.org/W7133229781"],"related_works":[],"abstract_inverted_index":{"Most":[0],"current":[1],"zero-shot":[2,93],"voice":[3,122],"conversion":[4],"methods":[5],"rely":[6],"on":[7,89],"externally":[8],"supervised":[9],"components,":[10],"particularly":[11],"speaker":[12,32,69,74,85],"encoders,":[13],"for":[14,57,121],"training.":[15],"To":[16],"explore":[17],"alternatives":[18],"that":[19,30,80],"eliminate":[20],"this":[21,23],"dependency,":[22],"paper":[24],"introduces":[25,102],"GenVC,":[26],"a":[27,41],"novel":[28],"framework":[29],"disentangles":[31],"identity":[33],"and":[34,48,72,113,116,130],"linguistic":[35],"content":[36],"from":[37],"speech":[38,46,58],"signals":[39],"in":[40,104],"self-supervised":[42],"manner.":[43],"GenVC":[44,81,101],"leverages":[45],"tokenizers":[47],"an":[49],"autoregressive,":[50],"Transformer-based":[51],"language":[52],"model":[53,131],"as":[54],"its":[55,98],"backbone":[56],"generation.":[59],"This":[60],"design":[61],"supports":[62],"large-scale":[63],"training":[64],"while":[65],"enhancing":[66],"both":[67],"source":[68,111],"privacy":[70],"protection":[71],"target":[73],"cloning":[75],"fidelity.":[76],"Experimental":[77],"results":[78],"demonstrate":[79],"achieves":[82],"notably":[83],"higher":[84],"similarity,":[86],"with":[87,91],"naturalness":[88],"par":[90],"leading":[92],"approaches.":[94],"Moreover,":[95],"due":[96],"to":[97],"autoregressive":[99],"formulation,":[100],"flexibility":[103],"temporal":[105],"alignment,":[106],"reducing":[107],"the":[108],"preservation":[109],"of":[110],"prosody":[112],"speaker-specific":[114],"traits,":[115],"making":[117],"it":[118],"highly":[119],"effective":[120],"anonymization.<sup":[123],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[124,126],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[125],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>Audio":[127],"samples,":[128],"code,":[129],"checkpoints":[132],"are":[133],"available":[134],"at":[135],"https://caizexin.github.io/GenVC/index.html":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-03T00:00:00"}
