{"id":"https://openalex.org/W4224916404","doi":"https://doi.org/10.1109/icassp43922.2022.9747743","title":"Training Robust Zero-Shot Voice Conversion Models with Self-Supervised Features","display_name":"Training Robust Zero-Shot Voice Conversion Models with Self-Supervised Features","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224916404","doi":"https://doi.org/10.1109/icassp43922.2022.9747743"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747743","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5040335961","display_name":"Trung Dang","orcid":"https://orcid.org/0009-0002-9914-5009"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Trung Dang","raw_affiliation_strings":["Boston University"],"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054814160","display_name":"Dung Viet Tran","orcid":"https://orcid.org/0000-0002-3673-9160"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Dung Tran","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113696329","display_name":"Peter Chin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Chin","raw_affiliation_strings":["Boston University"],"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084879161","display_name":"Kazuhito Koishida","orcid":"https://orcid.org/0000-0002-3111-5375"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kazuhito Koishida","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040335961"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8315,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73023055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6557","last_page":"6561"},"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":0.9995999932289124,"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/computer-science","display_name":"Computer science","score":0.8255782127380371},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.691864013671875},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6400494575500488},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49449941515922546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49229729175567627},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4916704297065735},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.47478052973747253},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4658777415752411},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4364716708660126},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4251546263694763},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.41453057527542114},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38915586471557617},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09438538551330566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8255782127380371},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.691864013671875},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6400494575500488},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49449941515922546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49229729175567627},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4916704297065735},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.47478052973747253},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4658777415752411},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4364716708660126},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4251546263694763},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.41453057527542114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38915586471557617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09438538551330566},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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:10.1109/icassp43922.2022.9747743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747743","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2476548250","https://openalex.org/W2527729766","https://openalex.org/W2532494225","https://openalex.org/W2804998325","https://openalex.org/W2945478979","https://openalex.org/W2963539064","https://openalex.org/W2972359262","https://openalex.org/W2972394484","https://openalex.org/W2972659941","https://openalex.org/W2973154337","https://openalex.org/W3015338123","https://openalex.org/W3015434413","https://openalex.org/W3036601975","https://openalex.org/W3097952294","https://openalex.org/W3126283728","https://openalex.org/W3143523927","https://openalex.org/W3161627112","https://openalex.org/W3163475957","https://openalex.org/W3168719651","https://openalex.org/W3197763626","https://openalex.org/W3198034710","https://openalex.org/W4297808394","https://openalex.org/W4301371414","https://openalex.org/W6727697161","https://openalex.org/W6728445508","https://openalex.org/W6762533536","https://openalex.org/W6780218876","https://openalex.org/W6785185317","https://openalex.org/W6790622591","https://openalex.org/W6796756982","https://openalex.org/W6803547063","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W4255044973","https://openalex.org/W2890936991","https://openalex.org/W2499802997","https://openalex.org/W2112059504","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2548037963","https://openalex.org/W2464377622","https://openalex.org/W2394963835"],"abstract_inverted_index":{"Unsupervised":[0],"Zero-Shot":[1],"Voice":[2],"Conversion":[3],"(VC)":[4],"aims":[5],"to":[6,14,35,48,75,89,143,166],"modify":[7],"the":[8,72,92,106,111,125,158,167,173],"speaker":[9,19,138,147],"characteristic":[10],"of":[11,29,120,185],"an":[12,16],"utterance":[13],"match":[15],"unseen":[17],"target":[18,168],"without":[20,40,86],"relying":[21],"on":[22,91,105,152],"parallel":[23],"training":[24],"data.":[25],"Recently,":[26],"self-supervised":[27],"learning":[28],"speech":[30],"representation":[31],"has":[32],"been":[33],"shown":[34],"produce":[36],"useful":[37],"linguistic":[38,81,174],"units":[39],"using":[41,65,118,154],"transcripts,":[42],"which":[43,70],"can":[44,61,101,141],"be":[45,62],"directly":[46],"passed":[47],"a":[49,66,130,137,145],"VC":[50,73],"model.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,113],"showed":[56,97],"that":[57,98,116,176],"high-quality":[58],"audio":[59,122,162],"samples":[60,163],"achieved":[63],"by":[64],"length":[67],"resampling":[68],"decoder,":[69],"enables":[71],"model":[74,150],"work":[76],"in":[77,183],"conjunction":[78],"with":[79,179],"different":[80,121],"feature":[82],"extractors":[83],"and":[84,134],"vocoders":[85],"requiring":[87],"them":[88],"operate":[90],"same":[93,126],"sequence":[94],"length.":[95],"We":[96],"our":[99],"method":[100],"outperform":[102],"many":[103],"baselines":[104],"VCTK":[107],"dataset.":[108],"Without":[109],"modifying":[110],"architecture,":[112],"further":[114],"demonstrated":[115],"a)":[117],"pairs":[119],"segments":[123],"from":[124],"speaker,":[127],"b)":[128],"adding":[129,136],"cycle":[131],"consistency":[132],"loss,":[133],"c)":[135],"classification":[139],"loss":[140],"help":[142],"learn":[144],"better":[146],"embedding.":[148],"Our":[149],"trained":[151],"LibriTTS":[153],"these":[155],"techniques":[156],"achieves":[157],"best":[159],"performance,":[160],"producing":[161],"transferred":[164],"well":[165],"speaker\u2019s":[169],"voice,":[170],"while":[171],"preserving":[172],"content":[175],"is":[177],"comparable":[178],"actual":[180],"human":[181],"utterances":[182],"terms":[184],"Character":[186],"Error":[187],"Rate.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}