{"id":"https://openalex.org/W4291286692","doi":"https://doi.org/10.48550/arxiv.2202.10020","title":"AVQVC: One-shot Voice Conversion by Vector Quantization with applying contrastive learning","display_name":"AVQVC: One-shot Voice Conversion by Vector Quantization with applying contrastive learning","publication_year":2022,"publication_date":"2022-02-21","ids":{"openalex":"https://openalex.org/W4291286692","doi":"https://doi.org/10.48550/arxiv.2202.10020"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2202.10020","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.10020","pdf_url":"https://arxiv.org/pdf/2202.10020","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2202.10020","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070815163","display_name":"Huaizhen Tang","orcid":"https://orcid.org/0000-0002-0414-8497","observed_orcids":["https://orcid.org/0000-0002-0414-8497"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tang, Huaizhen","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co. , Ltd","University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co. , Ltd","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028437800","display_name":"Xulong Zhang","orcid":"https://orcid.org/0000-0001-7005-992X","observed_orcids":["https://orcid.org/0000-0001-7005-992X"]},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Xulong","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co. , Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co. , Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231","observed_orcids":["https://orcid.org/0000-0002-9237-4231"]},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Jianzong","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co. , Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co. , Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977180","display_name":"Ning Cheng","orcid":"https://orcid.org/0000-0002-0988-5023","observed_orcids":["https://orcid.org/0000-0002-0988-5023"]},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng, Ning","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co. , Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co. , Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100721756","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0002-0573-8106","observed_orcids":["https://orcid.org/0000-0002-0573-8106"]},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao, Jing","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co. , Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co. , Ltd","institution_ids":["https://openalex.org/I4401726822"]}]}],"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":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937000274658203,"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":0.9937000274658203,"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":0.005400000140070915,"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/T10863","display_name":"Voice and Speech Disorders","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/voice-conversion","display_name":"voice conversion","score":0.8230000138282776},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"vector quantization","score":0.9900000095367432},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.9629999995231628},{"id":"https://openalex.org/keywords/disentangled-representation-learning","display_name":"disentangled representation learning","score":0.7070000171661377},{"id":"https://openalex.org/keywords/synthetic-speech-quality","display_name":"synthetic speech quality","score":0.3499999940395355}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8770202398300171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7122153639793396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6909664869308472},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6538609266281128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3075292110443115},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.06509825587272644},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2202.10020","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.10020","pdf_url":"https://arxiv.org/pdf/2202.10020","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2202.10020","doi":"https://doi.org/10.48550/arxiv.2202.10020","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2202.10020","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2202.10020","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.10020","pdf_url":"https://arxiv.org/pdf/2202.10020","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4291286692.pdf","grobid_xml":"https://content.openalex.org/works/W4291286692.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4297808394"],"related_works":["https://openalex.org/W4375868810","https://openalex.org/W3015434413","https://openalex.org/W4416800052","https://openalex.org/W3197659778","https://openalex.org/W3154134465","https://openalex.org/W7160844665","https://openalex.org/W4296068587","https://openalex.org/W4295895242","https://openalex.org/W3097045280","https://openalex.org/W3096524539"],"abstract_inverted_index":{"Voice":[0],"Conversion(VC)":[1],"refers":[2],"to":[3,24,72,74,100],"changing":[4],"the":[5,12,26,29,102],"timbre":[6,27,78,99],"of":[7,105],"a":[8,34,49],"speech":[9,35,81],"while":[10],"retaining":[11],"discourse":[13],"content.":[14],"Recently,":[15],"many":[16],"works":[17],"have":[18],"focused":[19],"on":[20,56],"disentangle-based":[21],"learning":[22],"techniques":[23],"separate":[25,75],"and":[28,44,62,77,98],"linguistic":[30],"content":[31,76,97],"information":[32,79],"from":[33,80],"signal.":[36],"Once":[37],"successful,":[38],"voice":[39,52,59],"conversion":[40,53,60],"will":[41],"be":[42],"feasible":[43],"straightforward.":[45],"This":[46],"paper":[47],"proposed":[48],"novel":[50],"one-shot":[51],"framework":[54],"based":[55],"vector":[57],"quantization":[58],"(VQVC)":[61],"AutoVC,":[63],"called":[64],"AVQVC.":[65],"A":[66],"new":[67],"training":[68],"method":[69],"is":[70],"applied":[71],"VQVC":[73,94],"more":[82],"effectively.":[83],"The":[84],"result":[85],"shows":[86],"that":[87],"this":[88],"approach":[89],"has":[90],"better":[91],"performance":[92],"than":[93],"in":[95],"separating":[96],"improve":[101],"sound":[103],"quality":[104],"generated":[106],"speech.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-08-14T00:00:00"}