{"id":"https://openalex.org/W3178966533","doi":"https://doi.org/10.21437/interspeech.2021-2086","title":"Many-to-Many Voice Conversion Based Feature Disentanglement Using Variational Autoencoder","display_name":"Many-to-Many Voice Conversion Based Feature Disentanglement Using Variational Autoencoder","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3178966533","doi":"https://doi.org/10.21437/interspeech.2021-2086","mag":"3178966533"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-2086","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2086","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.06642","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049516896","display_name":"Manh Luong","orcid":"https://orcid.org/0000-0003-2754-4609"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Manh Luong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101717726","display_name":"Viet Anh Tran","orcid":"https://orcid.org/0000-0001-9704-2669"},"institutions":[{"id":"https://openalex.org/I36085230","display_name":"Universit\u00e9 Stendhal \u2013 Grenoble 3","ror":"https://ror.org/03yppfm65","country_code":"FR","type":"education","lineage":["https://openalex.org/I36085230","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Viet Anh Tran","raw_affiliation_strings":["Universit\u00e9 Stendhal \u2013 Grenoble 3, Saint-Martin-d'H\u00e8res, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Stendhal \u2013 Grenoble 3, Saint-Martin-d'H\u00e8res, France","institution_ids":["https://openalex.org/I36085230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049516896"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09016411,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"851","last_page":"855"},"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":0.9966999888420105,"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":0.9905999898910522,"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/naturalness","display_name":"Naturalness","score":0.8832587003707886},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8770137429237366},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7456480264663696},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6652693748474121},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.6534614562988281},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6262274980545044},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5449709892272949},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5277139544487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44365808367729187},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4331128001213074},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3539603650569916},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2865999937057495},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.193482905626297},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07603177428245544},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07173869013786316}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8832587003707886},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8770137429237366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7456480264663696},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6652693748474121},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6534614562988281},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6262274980545044},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5449709892272949},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5277139544487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44365808367729187},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4331128001213074},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3539603650569916},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2865999937057495},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.193482905626297},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07603177428245544},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07173869013786316},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-2086","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2086","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"},{"id":"pmh:oai:arXiv.org:2107.06642","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.06642","pdf_url":"https://arxiv.org/pdf/2107.06642","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"mag:3178966533","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2107.06642.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2107.06642","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.06642","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.06642","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.06642","pdf_url":"https://arxiv.org/pdf/2107.06642","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3178966533.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2005438552","https://openalex.org/W2108501770","https://openalex.org/W2120605154","https://openalex.org/W2156142001","https://openalex.org/W2402324096","https://openalex.org/W2527729766","https://openalex.org/W2532494225","https://openalex.org/W2753738274","https://openalex.org/W2808697642","https://openalex.org/W2887264325","https://openalex.org/W2949281321","https://openalex.org/W2949382160","https://openalex.org/W2952161038","https://openalex.org/W2963618559","https://openalex.org/W2963830550","https://openalex.org/W2964243274","https://openalex.org/W2964812973","https://openalex.org/W2972667718","https://openalex.org/W2972849140","https://openalex.org/W3005031238","https://openalex.org/W3015805741","https://openalex.org/W3015959238","https://openalex.org/W3034058691","https://openalex.org/W3092246895","https://openalex.org/W3126283728"],"related_works":["https://openalex.org/W3198034710","https://openalex.org/W3030987249","https://openalex.org/W3015805741","https://openalex.org/W2937343983","https://openalex.org/W3163929126","https://openalex.org/W3046998876","https://openalex.org/W2122968425","https://openalex.org/W3176939825","https://openalex.org/W2398196429","https://openalex.org/W2790216641","https://openalex.org/W2742719288","https://openalex.org/W3135780427","https://openalex.org/W292968312","https://openalex.org/W3004606968","https://openalex.org/W3015699566","https://openalex.org/W2099797668","https://openalex.org/W3143523927","https://openalex.org/W2332932830","https://openalex.org/W3046954891","https://openalex.org/W2124667332"],"abstract_inverted_index":{"Voice":[0,31],"conversion":[1],"is":[2],"a":[3,12,16,68,108],"challenging":[4],"task":[5],"which":[6],"transforms":[7],"the":[8,46,85,117,131],"voice":[9,80],"characteristics":[10],"of":[11,134,145],"source":[13,101],"speaker":[14,18,50,61,89,120,149],"to":[15,48,55,75,78,87,103,129],"target":[17,105,119,148],"without":[19],"changing":[20],"linguistic":[21,53,92],"content.":[22],"Recently,":[23],"there":[24],"have":[25],"been":[26],"many":[27,77,79,100,104],"works":[28],"on":[29,35,59,72],"many-to-many":[30],"Conversion":[32],"(VC)":[33],"based":[34,71],"Variational":[36],"Autoencoder":[37],"(VAEs)":[38],"achieving":[39],"good":[40,57],"results,":[41],"however,":[42],"these":[43],"methods":[44],"lack":[45],"ability":[47],"disentangle":[49,88],"identity":[51,90],"and":[52,91,126,147],"content":[54,93],"achieve":[56],"performance":[58,133],"unseen":[60,118],"scenarios.":[62,121],"In":[63],"this":[64],"paper,":[65],"we":[66],"propose":[67],"new":[69],"method":[70,83,137],"feature":[73],"disentanglement":[74],"tackle":[76],"conversion.":[81],"The":[82],"has":[84],"capability":[86],"from":[94,99],"utterances,":[95],"it":[96,113],"can":[97],"convert":[98],"speakers":[102,106],"with":[107,116,139],"single":[109],"autoencoder":[110],"network.":[111],"Moreover,":[112],"naturally":[114],"deals":[115],"We":[122],"perform":[123],"both":[124],"objective":[125],"subjective":[127],"evaluations":[128],"show":[130],"competitive":[132],"our":[135],"proposed":[136],"compared":[138],"other":[140],"state-of-the-art":[141],"models":[142],"in":[143],"terms":[144],"naturalness":[146],"similarity.":[150]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}