{"id":"https://openalex.org/W4385823472","doi":"https://doi.org/10.21437/interspeech.2023-2298","title":"End-to-End Zero-Shot Voice Conversion with Location-Variable Convolutions","display_name":"End-to-End Zero-Shot Voice Conversion with Location-Variable Convolutions","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823472","doi":"https://doi.org/10.21437/interspeech.2023-2298"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2298","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5052061361","display_name":"Wonjune Kang","orcid":"https://orcid.org/0000-0001-5260-9094"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wonjune Kang","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004281470","display_name":"Deb Roy","orcid":"https://orcid.org/0000-0002-2780-4768"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deb Roy","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2303","last_page":"2307"},"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":0.9980999827384949,"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":0.994700014591217,"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":0.850075900554657},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6930484771728516},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.534538745880127},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5326245427131653},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4791145324707031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25739574432373047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.850075900554657},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6930484771728516},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.534538745880127},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5326245427131653},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4791145324707031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25739574432373047},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-2298","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2049304293","https://openalex.org/W2515028311","https://openalex.org/W2519091744","https://openalex.org/W2593414223","https://openalex.org/W2808631503","https://openalex.org/W2908510526","https://openalex.org/W2937579788","https://openalex.org/W2945478979","https://openalex.org/W2962896155","https://openalex.org/W2970006822","https://openalex.org/W2972359262","https://openalex.org/W2972659941","https://openalex.org/W2979826702","https://openalex.org/W3013020904","https://openalex.org/W3015338123","https://openalex.org/W3015805741","https://openalex.org/W3036601975","https://openalex.org/W3090254849","https://openalex.org/W3092028330","https://openalex.org/W3095361818","https://openalex.org/W3097777922","https://openalex.org/W3098557217","https://openalex.org/W3126283728","https://openalex.org/W3130774171","https://openalex.org/W3163475957","https://openalex.org/W3168719651","https://openalex.org/W3196475561","https://openalex.org/W3197273793","https://openalex.org/W3198429080","https://openalex.org/W3214606349","https://openalex.org/W4238674002","https://openalex.org/W4288337064","https://openalex.org/W4301371414","https://openalex.org/W4385993772"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2081919107","https://openalex.org/W2127461790","https://openalex.org/W2069324367","https://openalex.org/W3115948027","https://openalex.org/W2405110677","https://openalex.org/W2811496854","https://openalex.org/W127416991"],"abstract_inverted_index":{"Zero-shot":[0],"voice":[1,61,106,124],"conversion":[2,62,73,107],"is":[3],"becoming":[4],"an":[5,58],"increasingly":[6],"popular":[7],"research":[8],"topic,":[9],"as":[10],"it":[11,91],"promises":[12],"the":[13,41,72],"ability":[14],"to":[15,18,47,69,100,131],"transform":[16],"speech":[17,75,128],"sound":[19],"like":[20],"any":[21],"speaker.However,":[22],"relatively":[23],"little":[24],"work":[25],"has":[26],"been":[27],"done":[28],"on":[29],"end-to-end":[30,59],"methods":[31],"for":[32,43],"this":[33,53],"task,":[34],"which":[35],"are":[36],"appealing":[37],"because":[38],"they":[39],"remove":[40],"need":[42],"a":[44,93],"separate":[45],"vocoder":[46],"generate":[48],"audio":[49],"from":[50],"intermediate":[51],"features.In":[52],"work,":[54],"we":[55],"propose":[56],"LVC-VC,":[57],"zero-shot":[60],"model":[63,71,117],"that":[64,83,97,115],"uses":[65,92],"location-variable":[66],"convolutions":[67],"(LVCs)":[68],"jointly":[70],"and":[74,87,90,104,127],"synthesis":[76],"processes.LVC-VC":[77],"utilizes":[78,98],"carefully":[79],"designed":[80],"input":[81],"features":[82],"have":[84],"disentangled":[85],"content":[86],"speaker":[88],"information,":[89],"neural":[94],"vocoder-like":[95],"architecture":[96],"LVCs":[99],"efficiently":[101],"combine":[102],"them":[103],"perform":[105],"while":[108],"directly":[109],"synthesizing":[110],"time":[111],"domain":[112],"audio.Experiments":[113],"show":[114],"our":[116],"achieves":[118],"especially":[119],"well":[120],"balanced":[121],"performance":[122],"between":[123],"style":[125],"transfer":[126],"intelligibility":[129],"compared":[130],"several":[132],"baselines.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2023-08-15T00:00:00"}