{"id":"https://openalex.org/W3171025350","doi":"https://doi.org/10.21437/ssw.2021-20","title":"Voicy: Zero-Shot Non-Parallel Voice Conversion in Noisy Reverberant Environments","display_name":"Voicy: Zero-Shot Non-Parallel Voice Conversion in Noisy Reverberant Environments","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3171025350","doi":"https://doi.org/10.21437/ssw.2021-20","mag":"3171025350"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2021-20","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-20","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.08873","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012793114","display_name":"Alejandro Mottini","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alejandro Mottini","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066855316","display_name":"Sri Karlapati","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sri Vishnu Kumar Karlapati","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029023520","display_name":"Thomas Drugman","orcid":"https://orcid.org/0000-0002-1491-7878"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Drugman","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"113","last_page":"117"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.751895546913147},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7397517561912537},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7246450185775757},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.659985363483429},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4944272041320801},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.47069859504699707},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4222319722175598},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14389362931251526},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07331222295761108}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.751895546913147},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7397517561912537},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7246450185775757},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.659985363483429},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4944272041320801},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.47069859504699707},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4222319722175598},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14389362931251526},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07331222295761108},{"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},{"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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/ssw.2021-20","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-20","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.08873","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.08873","pdf_url":"https://arxiv.org/pdf/2106.08873","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3171025350","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.08873.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2106.08873","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.08873","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.08873","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.08873","pdf_url":"https://arxiv.org/pdf/2106.08873","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3171025350.pdf","grobid_xml":"https://content.openalex.org/works/W3171025350.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1509691205","https://openalex.org/W1983108229","https://openalex.org/W2013996527","https://openalex.org/W2017425464","https://openalex.org/W2025768430","https://openalex.org/W2056852181","https://openalex.org/W2121973264","https://openalex.org/W2136682440","https://openalex.org/W2156142001","https://openalex.org/W2164502538","https://openalex.org/W2191779130","https://openalex.org/W2527729766","https://openalex.org/W2576309025","https://openalex.org/W2577350056","https://openalex.org/W2747874407","https://openalex.org/W2763188033","https://openalex.org/W2804998325","https://openalex.org/W2887264325","https://openalex.org/W2949281321","https://openalex.org/W2954386831","https://openalex.org/W2962788625","https://openalex.org/W2963035245","https://openalex.org/W2963539064","https://openalex.org/W2970351109","https://openalex.org/W2997069303","https://openalex.org/W3105124182"],"related_works":["https://openalex.org/W3194805633","https://openalex.org/W3212441973","https://openalex.org/W3200209270","https://openalex.org/W2724603107","https://openalex.org/W2177286092","https://openalex.org/W3015231328","https://openalex.org/W3162577490","https://openalex.org/W3116834994","https://openalex.org/W3209376089","https://openalex.org/W3164223074","https://openalex.org/W3011500442","https://openalex.org/W3205533980","https://openalex.org/W2940526039","https://openalex.org/W1840572374","https://openalex.org/W3031135612","https://openalex.org/W3196660995","https://openalex.org/W3091830790","https://openalex.org/W3037737213","https://openalex.org/W3207551191","https://openalex.org/W2096594917"],"abstract_inverted_index":{"Voice":[0],"Conversion":[1],"(VC)":[2],"is":[3,27,82,89,104],"a":[4,14,28,70,134],"technique":[5],"that":[6,118,145],"aims":[7],"to":[8,17,60,120],"transform":[9],"the":[10,19,23,54,85,139],"non-linguistic":[11],"information":[12],"of":[13,22,56,91,106,138,154],"source":[15],"utterance":[16],"change":[18],"perceived":[20],"identity":[21],"speaker.":[24],"While":[25],"there":[26],"rich":[29],"literature":[30],"on":[31,40,122],"VC,":[32,110],"most":[33],"proposed":[34],"methods":[35,59],"are":[36,48],"trained":[37],"and":[38,50,97,99,156],"evaluated":[39],"clean":[41],"speech":[42],"recordings.":[43],"However,":[44],"many":[45],"acoustic":[46],"environments":[47],"noisy":[49,77,135,161],"reverberant,":[51],"severely":[52],"restricting":[53],"applicability":[55],"popular":[57],"VC":[58,72,116,150],"such":[61],"scenarios.":[62],"To":[63],"address":[64],"this":[65],"limitation,":[66],"we":[67],"propose":[68],"Voicy,":[69],"new":[71],"framework":[73],"particularly":[74],"tailored":[75],"for":[76,114],"speech.":[78],"Our":[79],"method,":[80],"which":[81],"inspired":[83],"by":[84],"de-noising":[86],"auto-encoders":[87],"framework,":[88],"comprised":[90],"four":[92],"encoders":[93],"(speaker,":[94],"content,":[95],"phonetic":[96],"acoustic-ASR)":[98],"one":[100],"decoder.":[101],"Importantly,":[102],"Voicy":[103,146],"capable":[105],"performing":[107],"non-parallel":[108],"zero-shot":[109],"an":[111],"important":[112],"requirement":[113],"any":[115],"system":[117],"needs":[119],"work":[121],"speakers":[123],"not":[124],"seen":[125],"during":[126],"training.":[127],"We":[128],"have":[129],"validated":[130],"our":[131],"approach":[132],"using":[133],"reverberant":[136,162],"version":[137],"LibriSpeech":[140],"dataset.":[141],"Experimental":[142],"results":[143],"show":[144],"outperforms":[147],"other":[148],"tested":[149],"techniques":[151],"in":[152,160],"terms":[153],"naturalness":[155],"target":[157],"speaker":[158],"similarity":[159],"environments.":[163]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
