{"id":"https://openalex.org/W4392904717","doi":"https://doi.org/10.1109/icassp48485.2024.10446296","title":"Unifying One-Shot Voice Conversion and Cloning with Disentangled Speech Representations","display_name":"Unifying One-Shot Voice Conversion and Cloning with Disentangled Speech Representations","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904717","doi":"https://doi.org/10.1109/icassp48485.2024.10446296"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101486499","display_name":"Hui Lu","orcid":"https://orcid.org/0000-0002-7698-6262"},"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":"Hui Lu","raw_affiliation_strings":["The Chinese University of Hong Kong,China","Center for Perceptual and Interactive Intelligence (CPII) Ltd, China","The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Center for Perceptual and Interactive Intelligence (CPII) Ltd, China","institution_ids":[]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"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":"Xixin Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,China","Center for Perceptual and Interactive Intelligence (CPII) Ltd, China","The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Center for Perceptual and Interactive Intelligence (CPII) Ltd, China","institution_ids":[]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072447806","display_name":"Haohan Guo","orcid":"https://orcid.org/0000-0002-3393-9984"},"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":"Haohan Guo","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102778496","display_name":"Songxiang Liu","orcid":"https://orcid.org/0000-0002-0943-2446"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songxiang Liu","raw_affiliation_strings":["Tencent,Tencent AI Lab,Shenzhen,China","Tencent AI Lab, Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Tencent AI Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"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"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, 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"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,China","Center for Perceptual and Interactive Intelligence (CPII) Ltd, China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Center for Perceptual and Interactive Intelligence (CPII) Ltd, China","institution_ids":[]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4224,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82025284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"11141","last_page":"11145"},"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":0.9965000152587891,"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":0.9861000180244446,"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/cloning","display_name":"Cloning (programming)","score":0.8631067872047424},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7173464894294739},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6643712520599365},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6533835530281067},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6274290084838867},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5173903703689575},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.49761345982551575},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.4215867221355438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41255512833595276}],"concepts":[{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.8631067872047424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7173464894294739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6643712520599365},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6533835530281067},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6274290084838867},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5173903703689575},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.49761345982551575},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.4215867221355438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41255512833595276},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2156142001","https://openalex.org/W2747329762","https://openalex.org/W2788357188","https://openalex.org/W2804998325","https://openalex.org/W2972359262","https://openalex.org/W2972659941","https://openalex.org/W2974231335","https://openalex.org/W2998572311","https://openalex.org/W3083423753","https://openalex.org/W3092028330","https://openalex.org/W3095990227","https://openalex.org/W3165478005","https://openalex.org/W3196584150","https://openalex.org/W3197659778","https://openalex.org/W3203614938","https://openalex.org/W4212774754","https://openalex.org/W4225329057","https://openalex.org/W4284690259","https://openalex.org/W4289761690","https://openalex.org/W4297841465","https://openalex.org/W4297841574","https://openalex.org/W4319862209","https://openalex.org/W6640963894","https://openalex.org/W6744627333","https://openalex.org/W6745117592","https://openalex.org/W6748588790","https://openalex.org/W6752910514","https://openalex.org/W6767671539","https://openalex.org/W6772349387","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6796464841"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"We":[0],"propose":[1],"unifying":[2],"one-shot":[3,104,123],"voice":[4,105,124,131],"conversion":[5,106,125,132],"and":[6,36,76,107,126,133],"cloning":[7,127,134],"into":[8,34],"a":[9,22,26,42,53,69],"single":[10],"model":[11,83],"that":[12,31,112],"can":[13,84],"be":[14],"end-to-end":[15],"optimized.":[16],"To":[17],"achieve":[18],"this,":[19],"we":[20,51],"introduce":[21],"novel":[23],"extension":[24],"to":[25,129],"speech":[27,33,95],"variational":[28],"auto-encoder":[29],"(VAE)":[30],"disentangles":[32],"content":[35,64,70,87],"speaker":[37,74],"representations.":[38],"Instead":[39],"of":[40],"using":[41,89],"fixed":[43],"Gaussian":[44],"prior":[45,56,99],"as":[46,57],"in":[47,68],"the":[48,63,86,91,97,113],"vanilla":[49],"VAE,":[50],"incorporate":[52],"learnable":[54],"text-aware":[55,98],"an":[58],"informative":[59],"guide":[60],"for":[61,122],"learning":[62],"representation.":[65],"This":[66],"results":[67],"representation":[71,88],"with":[72,100],"reduced":[73],"information":[75],"more":[77],"accurate":[78],"linguistic":[79],"information.":[80],"The":[81],"proposed":[82,114],"sample":[85],"either":[90],"posterior":[92],"conditioned":[93],"on":[94],"or":[96,118],"textual":[101],"input,":[102],"enabling":[103],"cloning,":[108],"respectively.":[109],"Experiments":[110],"show":[111],"method":[115],"achieves":[116],"better":[117],"comparable":[119],"overall":[120],"performance":[121],"compared":[128],"state-of-the-art":[130],"methods.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
