{"id":"https://openalex.org/W3197659778","doi":"https://doi.org/10.21437/interspeech.2021-283","title":"VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-Shot Voice Conversion","display_name":"VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-Shot Voice Conversion","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197659778","doi":"https://doi.org/10.21437/interspeech.2021-283","mag":"3197659778"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-283","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5068726270","display_name":"Disong Wang","orcid":"https://orcid.org/0000-0001-8481-6880"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Disong Wang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044738402","display_name":"Liqun Deng","orcid":"https://orcid.org/0009-0006-7242-0794"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Liqun Deng","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083831776","display_name":"Yu Ting Yeung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yu Ting Yeung","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373698","display_name":"Xiao Dong Chen","orcid":"https://orcid.org/0000-0002-0150-0491"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xiao Chen","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.0547,"has_fulltext":false,"cited_by_count":112,"citation_normalized_percentile":{"value":0.98697924,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1344","last_page":"1348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9811000227928162,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9545999765396118,"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/vector-quantization","display_name":"Vector quantization","score":0.7812846899032593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7350579500198364},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6464926600456238},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5648318529129028},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5498762130737305},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.516184389591217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40822333097457886},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11044782400131226}],"concepts":[{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.7812846899032593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7350579500198364},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6464926600456238},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5648318529129028},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5498762130737305},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.516184389591217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40822333097457886},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11044782400131226},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-283","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1862426464","https://openalex.org/W2105160541","https://openalex.org/W2120605154","https://openalex.org/W2124641009","https://openalex.org/W2152790380","https://openalex.org/W2161476805","https://openalex.org/W2166944917","https://openalex.org/W2518172956","https://openalex.org/W2527729766","https://openalex.org/W2576309025","https://openalex.org/W2774848319","https://openalex.org/W2787748320","https://openalex.org/W2803832867","https://openalex.org/W2888922217","https://openalex.org/W2945478979","https://openalex.org/W2962896155","https://openalex.org/W2963539064","https://openalex.org/W2972659941","https://openalex.org/W2972894903","https://openalex.org/W2973154337","https://openalex.org/W2973215447","https://openalex.org/W2979476256","https://openalex.org/W3015212100","https://openalex.org/W3015338123","https://openalex.org/W3015805741","https://openalex.org/W3034794073","https://openalex.org/W3036928441","https://openalex.org/W3095361818","https://openalex.org/W3096524539","https://openalex.org/W3097256596","https://openalex.org/W3125709657","https://openalex.org/W3126283728","https://openalex.org/W3163475957","https://openalex.org/W4235132546","https://openalex.org/W4297808394"],"related_works":["https://openalex.org/W2110652681","https://openalex.org/W1968634139","https://openalex.org/W3209251257","https://openalex.org/W2121067345","https://openalex.org/W1492958138","https://openalex.org/W2026546676","https://openalex.org/W1907918676","https://openalex.org/W1955747548","https://openalex.org/W2912686400","https://openalex.org/W2287895428"],"abstract_inverted_index":{"One-shot":[0],"voice":[1],"conversion":[2,6],"(VC),":[3],"which":[4,37],"performs":[5],"across":[7],"arbitrary":[8],"speakers":[9],"with":[10],"only":[11],"a":[12],"single":[13],"target-speaker":[14],"utterance":[15],"for":[16,60,106],"reference,":[17],"can":[18],"be":[19],"effectively":[20],"achieved":[21],"by":[22,84],"speech":[23,33,104,126],"representation":[24,46],"disentanglement.Existing":[25],"work":[26],"generally":[27],"ignores":[28],"the":[29,44,69,94,97,121],"correlation":[30,70],"between":[31],"different":[32],"representations":[34,105],"during":[35,72],"training,":[36,73],"causes":[38],"leakage":[39],"of":[40,78,96],"content":[41,61,110],"information":[42,66],"into":[43],"speaker":[45,80,117,129],"and":[47,63,81,111,128,140],"thus":[48],"degrades":[49],"VC":[50,135],"performance.To":[51],"alleviate":[52],"this":[53],"issue,":[54],"we":[55],"employ":[56],"vector":[57],"quantization":[58],"(VQ)":[59],"encoding":[62],"introduce":[64],"mutual":[65],"(MI)":[67],"as":[68],"metric":[71],"to":[74],"achieve":[75],"proper":[76],"disentanglement":[77],"content,":[79],"pitch":[82],"representations,":[83],"reducing":[85],"their":[86],"inter-dependencies":[87],"in":[88,100],"an":[89],"unsupervised":[90],"manner.Experimental":[91],"results":[92],"reflect":[93],"superiority":[95],"proposed":[98,122],"method":[99],"learning":[101],"effective":[102],"disentangled":[103],"retaining":[107],"source":[108],"linguistic":[109],"intonation":[112],"variations,":[113],"while":[114],"capturing":[115],"target":[116],"characteristics.In":[118],"doing":[119],"so,":[120],"approach":[123],"achieves":[124],"higher":[125],"naturalness":[127],"similarity":[130],"than":[131],"current":[132],"state-of-the-art":[133],"one-shot":[134],"systems.Our":[136],"code,":[137],"pre-trained":[138],"models":[139],"demo":[141],"are":[142],"available":[143],"at":[144],"https://github.com/Wendison/VQMIVC.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":40},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}