{"id":"https://openalex.org/W4312732823","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892405","title":"Zero-shot Voice Conversion via Self-supervised Prosody Representation Learning","display_name":"Zero-shot Voice Conversion via Self-supervised Prosody Representation Learning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312732823","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892405"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892405","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 International Joint Conference on Neural Networks (IJCNN)","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/A5100627209","display_name":"Shijun Wang","orcid":"https://orcid.org/0000-0001-7290-412X"},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]},{"id":"https://openalex.org/I4210145378","display_name":"University of Applied Sciences St. Gallen","ror":"https://ror.org/049bwzr51","country_code":"CH","type":"education","lineage":["https://openalex.org/I4210145378"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Shijun Wang","raw_affiliation_strings":["School of Computer Science University of St. Gallen,AIML Lab,St. Gallen,Switzerland","AIML Lab, School of Computer Science University of St. Gallen, St. Gallen, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science University of St. Gallen,AIML Lab,St. Gallen,Switzerland","institution_ids":["https://openalex.org/I202963720","https://openalex.org/I4210145378"]},{"raw_affiliation_string":"AIML Lab, School of Computer Science University of St. Gallen, St. Gallen, Switzerland","institution_ids":["https://openalex.org/I202963720"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065722787","display_name":"Damian Borth","orcid":"https://orcid.org/0000-0002-4660-2627"},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]},{"id":"https://openalex.org/I4210145378","display_name":"University of Applied Sciences St. Gallen","ror":"https://ror.org/049bwzr51","country_code":"CH","type":"education","lineage":["https://openalex.org/I4210145378"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Damian Borth","raw_affiliation_strings":["School of Computer Science University of St. Gallen,AIML Lab,St. Gallen,Switzerland","AIML Lab, School of Computer Science University of St. Gallen, St. Gallen, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science University of St. Gallen,AIML Lab,St. Gallen,Switzerland","institution_ids":["https://openalex.org/I202963720","https://openalex.org/I4210145378"]},{"raw_affiliation_string":"AIML Lab, School of Computer Science University of St. Gallen, St. Gallen, Switzerland","institution_ids":["https://openalex.org/I202963720"]}]}],"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":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"08"},"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":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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/prosody","display_name":"Prosody","score":0.9491066932678223},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7017426490783691},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6906265020370483},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.661154568195343},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5339037179946899},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5145470499992371},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.470229834318161},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45586302876472473},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4116480350494385},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37064552307128906},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10610556602478027}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9491066932678223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7017426490783691},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6906265020370483},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.661154568195343},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5339037179946899},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5145470499992371},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.470229834318161},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45586302876472473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4116480350494385},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37064552307128906},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10610556602478027},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892405","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1517202054","https://openalex.org/W2127520494","https://openalex.org/W2187089797","https://openalex.org/W2752796333","https://openalex.org/W2774848319","https://openalex.org/W2794490148","https://openalex.org/W2889061305","https://openalex.org/W2890964092","https://openalex.org/W2902070858","https://openalex.org/W2946809691","https://openalex.org/W2963306451","https://openalex.org/W2963539064","https://openalex.org/W2963799213","https://openalex.org/W2972659941","https://openalex.org/W2973049979","https://openalex.org/W3005680577","https://openalex.org/W3015338123","https://openalex.org/W3015434413","https://openalex.org/W3015645837","https://openalex.org/W3034794073","https://openalex.org/W3095361818","https://openalex.org/W3096524539","https://openalex.org/W3097892637","https://openalex.org/W3098557217","https://openalex.org/W3102628737","https://openalex.org/W3144810982","https://openalex.org/W3154134465","https://openalex.org/W3160950295","https://openalex.org/W3163475957","https://openalex.org/W3171007011","https://openalex.org/W3200019757","https://openalex.org/W4288337064","https://openalex.org/W4297808394","https://openalex.org/W6696991152","https://openalex.org/W6750489868","https://openalex.org/W6762983265","https://openalex.org/W6804007610"],"related_works":["https://openalex.org/W4214652783","https://openalex.org/W258725851","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W1965141925","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418"],"abstract_inverted_index":{"Voice":[0],"Conversion":[1],"(VC)":[2],"for":[3,126],"unseen":[4],"speakers,":[5],"also":[6],"known":[7],"as":[8,16,116],"zero-shot":[9,127,162],"VC,":[10],"is":[11],"an":[12],"attractive":[13],"research":[14],"topic":[15],"it":[17],"enables":[18],"a":[19,88],"range":[20],"of":[21,53,61,106,151],"applications":[22],"like":[23],"voice":[24,69],"customizing,":[25],"animation":[26],"production,":[27],"and":[28,44,97,121,140,159],"others.":[29],"Recent":[30],"work":[31],"in":[32,70,142],"this":[33,84],"area":[34],"made":[35],"progress":[36],"with":[37],"disentanglement":[38],"methods":[39,55],"that":[40,92,100,134,148],"separate":[41],"utterance":[42],"content":[43],"speaker":[45,68],"characteristics":[46],"from":[47,77],"speech":[48,73],"audio":[49],"recordings.":[50],"However,":[51],"many":[52],"these":[54],"are":[56,138],"subject":[57],"to":[58,74,119],"the":[59,67,71,78,103,112,149],"leakage":[60],"prosody":[62,104,136,143,153],"(e.g.,":[63],"pitch,":[64],"volume),":[65],"causing":[66],"synthesized":[72],"be":[75],"different":[76,107],"desired":[79],"target":[80],"speakers.":[81,108],"To":[82],"prevent":[83],"issue,":[85],"we":[86,132,146],"propose":[87],"novel":[89],"self-supervised":[90],"approach":[91],"effectively":[93],"learns":[94],"disentangled":[95,139],"pitch":[96],"volume":[98],"representations":[99,115,137,154],"can":[101],"represent":[102],"styles":[105],"We":[109],"then":[110],"use":[111],"learned":[113],"prosodic":[114],"conditional":[117],"information":[118],"train":[120],"enhance":[122],"our":[123,130,135,152,156],"VC":[124,157,163],"model":[125],"conversion.":[128],"In":[129],"experiments,":[131],"show":[133],"rich":[141],"information.":[144],"Moreover,":[145],"demonstrate":[147],"addition":[150],"improves":[155],"performance":[158],"surpasses":[160],"state-of-the-art":[161],"performances.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}