{"id":"https://openalex.org/W4372347529","doi":"https://doi.org/10.1109/icassp49357.2023.10095393","title":"DVQVC: An Unsupervised Zero-Shot Voice Conversion Framework","display_name":"DVQVC: An Unsupervised Zero-Shot Voice Conversion Framework","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372347529","doi":"https://doi.org/10.1109/icassp49357.2023.10095393"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5100647824","display_name":"Dayong Li","orcid":"https://orcid.org/0000-0002-1165-0303"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dayong Li","raw_affiliation_strings":["Westlake University & Westlake,Institute for Advanced Study,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Westlake University & Westlake,Institute for Advanced Study,Hangzhou,China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425999","display_name":"Xian Li","orcid":"https://orcid.org/0000-0001-5714-3940"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Li","raw_affiliation_strings":["Westlake University & Westlake,Institute for Advanced Study,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Westlake University & Westlake,Institute for Advanced Study,Hangzhou,China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100358320","display_name":"Xiaofei Li","orcid":"https://orcid.org/0000-0003-0393-9905"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Li","raw_affiliation_strings":["Westlake University & Westlake,Institute for Advanced Study,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Westlake University & Westlake,Institute for Advanced Study,Hangzhou,China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100647824"],"corresponding_institution_ids":["https://openalex.org/I3133055985"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5238044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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":0.995199978351593,"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/speech-recognition","display_name":"Speech recognition","score":0.8042653799057007},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7507749795913696},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7134495377540588},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6334950923919678},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5738075971603394},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5544885993003845},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49354588985443115},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4895382821559906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41297999024391174}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8042653799057007},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7507749795913696},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7134495377540588},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6334950923919678},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5738075971603394},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5544885993003845},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49354588985443115},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4895382821559906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41297999024391174},{"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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":35,"referenced_works":["https://openalex.org/W2471520273","https://openalex.org/W2791686384","https://openalex.org/W2808706139","https://openalex.org/W2979476256","https://openalex.org/W3005680577","https://openalex.org/W3035574324","https://openalex.org/W3036601975","https://openalex.org/W3043999252","https://openalex.org/W3082130377","https://openalex.org/W3092028330","https://openalex.org/W3094635600","https://openalex.org/W3096524539","https://openalex.org/W3162427973","https://openalex.org/W3196305160","https://openalex.org/W3197659778","https://openalex.org/W3197763626","https://openalex.org/W3205635414","https://openalex.org/W3206395542","https://openalex.org/W3207300132","https://openalex.org/W4200493871","https://openalex.org/W4221141917","https://openalex.org/W4225096077","https://openalex.org/W4225304461","https://openalex.org/W4226332109","https://openalex.org/W4319862670","https://openalex.org/W6752888775","https://openalex.org/W6769196770","https://openalex.org/W6774314701","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6802163632","https://openalex.org/W6802517614","https://openalex.org/W6840412704","https://openalex.org/W6849880362","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2938358845"],"abstract_inverted_index":{"Zero-shot":[0],"voice":[1],"conversion":[2],"(VC)":[3],"is":[4,43],"to":[5,11,44,89,98],"convert":[6],"speech":[7,25,55,102,121],"from":[8],"one":[9,23],"speaker":[10,14,47,68,72,82,124],"a":[12,35,62,78,81],"target":[13,30],"while":[15],"preserving":[16],"the":[17,28,91,101,105],"original":[18],"linguistic":[19],"information,":[20],"given":[21],"only":[22,109],"reference":[24],"clip":[26],"of":[27,119],"unseen":[29,130],"speaker.":[31],"This":[32],"work":[33],"proposes":[34],"new":[36],"VC":[37,115],"model,":[38],"and":[39,48,65,85,97,112,123,129],"its":[40],"key":[41],"idea":[42],"conduct":[45],"thorough":[46],"content":[49,63,92],"disentanglement":[50],"by":[51,95],"adopting":[52],"an":[53,66,86],"advanced":[54,67],"encoder":[56,69],"plus":[57],"vector":[58],"quantization":[59],"(VQ)":[60],"as":[61],"encoder,":[64],"for":[70,126],"accurate":[71],"embedding.":[73],"In":[74],"addition,":[75],"we":[76],"propose":[77],"perceptual":[79],"loss,":[80],"constrative":[83],"loss":[84,88],"adversarial":[87],"compensate":[90],"imperfection":[93],"caused":[94],"VQ":[96],"further":[99],"improve":[100],"quality/intelligibility.":[103],"Overall,":[104],"proposed":[106],"model":[107],"uses":[108],"unsupervised":[110],"features/losses,":[111],"achieves":[113],"excellent":[114],"performance":[116],"in":[117],"terms":[118],"both":[120,127],"quality/intelligibility":[122],"similarity,":[125],"seen":[128],"speakers.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}