{"id":"https://openalex.org/W2907262790","doi":"https://doi.org/10.1109/icassp.2019.8683561","title":"Disentangling Correlated Speaker and Noise for Speech Synthesis via Data Augmentation and Adversarial Factorization","display_name":"Disentangling Correlated Speaker and Noise for Speech Synthesis via Data Augmentation and Adversarial Factorization","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2907262790","doi":"https://doi.org/10.1109/icassp.2019.8683561","mag":"2907262790"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei-Ning Hsu","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron J. Weiss","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008107321","display_name":"Yu-An Chung","orcid":"https://orcid.org/0000-0001-9451-7956"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu-An Chung","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103854502","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0001-8269-3354"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010253402","display_name":"Yonghui Wu","orcid":"https://orcid.org/0000-0002-6780-6135"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonghui Wu","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5051950818"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":12.8609,"has_fulltext":false,"cited_by_count":115,"citation_normalized_percentile":{"value":0.9893723,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5901","last_page":"5905"},"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":0.9995999932289124,"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":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.7780731320381165},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7127106189727783},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5828676223754883},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5589538812637329},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5272461771965027},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.519001841545105},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.47255179286003113},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4333113729953766},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4164167642593384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3795391917228699},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.28407108783721924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7780731320381165},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7127106189727783},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5828676223754883},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5589538812637329},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5272461771965027},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.519001841545105},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.47255179286003113},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4333113729953766},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4164167642593384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3795391917228699},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.28407108783721924},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1574170747","https://openalex.org/W1731081199","https://openalex.org/W1956343362","https://openalex.org/W1959608418","https://openalex.org/W2114925438","https://openalex.org/W2131953535","https://openalex.org/W2187089797","https://openalex.org/W2527729766","https://openalex.org/W2559260703","https://openalex.org/W2559823555","https://openalex.org/W2587088898","https://openalex.org/W2617258110","https://openalex.org/W2619368999","https://openalex.org/W2753738274","https://openalex.org/W2758785877","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2796339975","https://openalex.org/W2808697642","https://openalex.org/W2808706139","https://openalex.org/W2884607399","https://openalex.org/W2952161038","https://openalex.org/W2962684181","https://openalex.org/W2962691331","https://openalex.org/W2962750142","https://openalex.org/W2962788625","https://openalex.org/W2963272440","https://openalex.org/W2963364041","https://openalex.org/W2963432880","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2963618559","https://openalex.org/W2963712897","https://openalex.org/W2963927338","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W4289383906","https://openalex.org/W4295731579","https://openalex.org/W6631190155","https://openalex.org/W6634468015","https://openalex.org/W6637618735","https://openalex.org/W6640850671","https://openalex.org/W6640963894","https://openalex.org/W6738277540","https://openalex.org/W6744627333","https://openalex.org/W6745117592","https://openalex.org/W6750489868","https://openalex.org/W6752753409","https://openalex.org/W6752888775","https://openalex.org/W6753540710","https://openalex.org/W6755300632","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W4285706568"],"abstract_inverted_index":{"To":[0],"leverage":[1],"crowd-sourced":[2],"data":[3,103],"to":[4,21,46,86,105,127,156],"train":[5],"multi-speaker":[6],"text-to-speech":[7],"(TTS)":[8],"models":[9],"that":[10,62,108,133],"can":[11,26,42,137,153],"synthesize":[12,158],"clean":[13,159],"speech":[14,160],"for":[15,161],"all":[16,162],"speakers,":[17],"it":[18],"is":[19,109,118],"essential":[20],"learn":[22],"disentangled":[23],"representations":[24,41],"which":[25],"independently":[27],"control":[28],"the":[29,47,52,60,78,134,149,167],"speaker":[30,113,139],"identity":[31,114],"and":[32,59,64,115,122,140,152],"background":[33],"noise":[34,107,141],"in":[35,148],"generated":[36],"signals.":[37],"However,":[38],"learning":[39],"such":[40],"be":[43,154],"challenging,":[44],"due":[45],"lack":[48],"of":[49,55,169],"labels":[50],"describing":[51],"recording":[53,65],"conditions":[54,66],"each":[56,170],"training":[57,150],"example,":[58],"fact":[61],"speakers":[63],"are":[67,146],"often":[68,73],"correlated,":[69],"e.g.":[70],"since":[71],"users":[72],"make":[74],"many":[75],"recordings":[76],"using":[77,102,124],"same":[79],"equipment.":[80],"This":[81],"paper":[82],"proposes":[83],"three":[84],"components":[85],"address":[87],"this":[88],"problem":[89],"by:":[90],"(1)":[91],"formulating":[92],"a":[93],"conditional":[94],"generative":[95],"model":[96],"with":[97,112],"factorized":[98],"latent":[99],"variables,":[100],"(2)":[101],"augmentation":[104],"add":[106],"not":[110],"correlated":[111,147],"whose":[116],"label":[117],"known":[119],"during":[120],"training,":[121],"(3)":[123],"adversarial":[125],"factorization":[126],"improve":[128],"disentanglement.":[129],"Experimental":[130],"results":[131],"demonstrate":[132],"proposed":[135,171],"method":[136],"disentangle":[138],"attributes":[142],"even":[143],"if":[144],"they":[145],"data,":[151],"used":[155],"consistently":[157],"speakers.":[163],"Ablation":[164],"studies":[165],"verify":[166],"importance":[168],"component.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":14}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}