{"id":"https://openalex.org/W3210530853","doi":"https://doi.org/10.1109/icassp43922.2022.9746484","title":"A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion","display_name":"A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3210530853","doi":"https://doi.org/10.1109/icassp43922.2022.9746484","mag":"3210530853"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746484","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.02392","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046382731","display_name":"Benjamin van Niekerk","orcid":"https://orcid.org/0000-0001-9207-6309"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]},{"id":"https://openalex.org/I4210104072","display_name":"Ubisoft (Canada)","ror":"https://ror.org/01hmp5p66","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210104072"]}],"countries":["CA","ZA"],"is_corresponding":true,"raw_author_name":"Benjamin van Niekerk","raw_affiliation_strings":["Ubisoft La Forge,Montreal,Canada","Ubisoft La Forge, Montreal, Canada","E&#x0026","E Engineering, Stellenbosch University, South Africa"],"affiliations":[{"raw_affiliation_string":"Ubisoft La Forge,Montreal,Canada","institution_ids":["https://openalex.org/I4210104072"]},{"raw_affiliation_string":"Ubisoft La Forge, Montreal, Canada","institution_ids":["https://openalex.org/I4210104072"]},{"raw_affiliation_string":"E&#x0026","institution_ids":[]},{"raw_affiliation_string":"E Engineering, Stellenbosch University, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030861649","display_name":"Marc\u2010Andr\u00e9 Carbonneau","orcid":"https://orcid.org/0000-0002-0677-415X"},"institutions":[{"id":"https://openalex.org/I4210104072","display_name":"Ubisoft (Canada)","ror":"https://ror.org/01hmp5p66","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210104072"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Marc-Andre Carbonneau","raw_affiliation_strings":["Ubisoft La Forge,Montreal,Canada","Ubisoft La Forge, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Ubisoft La Forge,Montreal,Canada","institution_ids":["https://openalex.org/I4210104072"]},{"raw_affiliation_string":"Ubisoft La Forge, Montreal, Canada","institution_ids":["https://openalex.org/I4210104072"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006300453","display_name":"Julian Za\u00efdi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104072","display_name":"Ubisoft (Canada)","ror":"https://ror.org/01hmp5p66","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210104072"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Julian Zaidi","raw_affiliation_strings":["Ubisoft La Forge,Montreal,Canada","Ubisoft La Forge, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Ubisoft La Forge,Montreal,Canada","institution_ids":["https://openalex.org/I4210104072"]},{"raw_affiliation_string":"Ubisoft La Forge, Montreal, Canada","institution_ids":["https://openalex.org/I4210104072"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085677838","display_name":"Matthew Baas","orcid":"https://orcid.org/0000-0003-3001-6292"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Matthew Baas","raw_affiliation_strings":["Stellenbosch University,E&#x0026;E Engineering,South Africa","E&#x0026"],"affiliations":[{"raw_affiliation_string":"Stellenbosch University,E&#x0026;E Engineering,South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"E&#x0026","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028028099","display_name":"Hugo Seut\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104072","display_name":"Ubisoft (Canada)","ror":"https://ror.org/01hmp5p66","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210104072"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hugo Seute","raw_affiliation_strings":["Ubisoft La Forge,Montreal,Canada","Ubisoft La Forge, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Ubisoft La Forge,Montreal,Canada","institution_ids":["https://openalex.org/I4210104072"]},{"raw_affiliation_string":"Ubisoft La Forge, Montreal, Canada","institution_ids":["https://openalex.org/I4210104072"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040305929","display_name":"Herman Kamper","orcid":"https://orcid.org/0000-0003-2980-3475"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["Stellenbosch University,E&#x0026;E Engineering,South Africa","E&#x0026"],"affiliations":[{"raw_affiliation_string":"Stellenbosch University,E&#x0026;E Engineering,South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"E&#x0026","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5046382731"],"corresponding_institution_ids":["https://openalex.org/I26092322","https://openalex.org/I4210104072"],"apc_list":null,"apc_paid":null,"fwci":10.4315,"has_fulltext":false,"cited_by_count":107,"citation_normalized_percentile":{"value":0.98892422,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6562","last_page":"6566"},"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":0.9973999857902527,"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/T12031","display_name":"Speech and dialogue systems","score":0.9921000003814697,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6604983806610107},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6060488224029541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6604983806610107},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6060488224029541}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746484","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"},{"id":"pmh:oai:arXiv.org:2111.02392","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.02392","pdf_url":"https://arxiv.org/pdf/2111.02392","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2111.02392","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.02392","pdf_url":"https://arxiv.org/pdf/2111.02392","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2120605154","https://openalex.org/W2155490028","https://openalex.org/W2395718496","https://openalex.org/W2518172956","https://openalex.org/W2519091744","https://openalex.org/W2750167318","https://openalex.org/W2805993470","https://openalex.org/W2842511635","https://openalex.org/W2890964092","https://openalex.org/W2899877258","https://openalex.org/W2945478979","https://openalex.org/W2949281321","https://openalex.org/W2949382160","https://openalex.org/W2963539064","https://openalex.org/W2964243274","https://openalex.org/W2972802841","https://openalex.org/W2995181338","https://openalex.org/W3015877095","https://openalex.org/W3082130377","https://openalex.org/W3092028330","https://openalex.org/W3092368332","https://openalex.org/W3095361818","https://openalex.org/W3098403858","https://openalex.org/W3110458199","https://openalex.org/W3140429000","https://openalex.org/W3161695192","https://openalex.org/W3169320628","https://openalex.org/W3188160682","https://openalex.org/W3197580070","https://openalex.org/W3198815374","https://openalex.org/W3209059054","https://openalex.org/W4287591426","https://openalex.org/W4288079605","https://openalex.org/W4288079962","https://openalex.org/W4289299319","https://openalex.org/W4297808394","https://openalex.org/W6752124048","https://openalex.org/W6762533536","https://openalex.org/W6783867762","https://openalex.org/W6786696081","https://openalex.org/W6840412704","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,90],"voice":[3,28],"conversion":[4],"is":[5],"to":[6,57],"transform":[7],"source":[8],"speech":[9,36,65],"into":[10],"a":[11,60,70],"target":[12],"voice,":[13],"keeping":[14],"the":[15,73,86],"content":[16,54,83],"unchanged.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21,31,62],"focus":[22],"on":[23],"self-supervised":[24],"representation":[25],"learning":[26],"for":[27],"conversion.":[29],"Specifically,":[30],"compare":[32],"discrete":[33,44,74],"and":[34,88],"soft":[35,64,79],"units":[37,66,80],"as":[38],"input":[39],"features.":[40],"We":[41],"find":[42],"that":[43],"representations":[45],"effectively":[46],"remove":[47],"speaker":[48],"information":[49],"but":[50],"discard":[51],"some":[52],"linguistic":[53],"&#x2013;":[55],"leading":[56],"mispronunciations.":[58],"As":[59],"solution,":[61],"propose":[63],"learned":[67],"by":[68],"predicting":[69],"distribution":[71],"over":[72],"units.":[75],"By":[76],"modeling":[77],"uncertainty,":[78],"capture":[81],"more":[82],"information,":[84],"improving":[85],"intelligibility":[87],"naturalness":[89],"converted":[91],"speech.<sup>1</sup><sup>2</sup>":[92]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":36},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2021-11-08T00:00:00"}