{"id":"https://openalex.org/W3160567113","doi":"https://doi.org/10.1109/waspaa52581.2021.9632676","title":"Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement","display_name":"Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3160567113","doi":"https://doi.org/10.1109/waspaa52581.2021.9632676","mag":"3160567113"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.08970","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023952427","display_name":"Guillaume Carbajal","orcid":"https://orcid.org/0000-0003-4077-1742"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Guillaume Carbajal","raw_affiliation_strings":["Signal Processing (SP), Universit\u00e4t, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Signal Processing (SP), Universit\u00e4t, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087017732","display_name":"Julius Richter","orcid":"https://orcid.org/0000-0002-7870-4839"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julius Richter","raw_affiliation_strings":["Signal Processing (SP), Universit\u00e4t, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Signal Processing (SP), Universit\u00e4t, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087022569","display_name":"Timo Gerkmann","orcid":"https://orcid.org/0000-0002-8678-4699"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo Gerkmann","raw_affiliation_strings":["Signal Processing (SP), Universit\u00e4t, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Signal Processing (SP), Universit\u00e4t, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023952427"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":1.8468,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85665392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":0.9969000220298767,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/audio-visual","display_name":"Audio visual","score":0.7784383893013},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7236976623535156},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5915059447288513},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5656394362449646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4286750257015228},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.20484721660614014},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.047359973192214966}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7784383893013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7236976623535156},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5915059447288513},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5656394362449646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4286750257015228},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.20484721660614014},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.047359973192214966}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.08970","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.08970","pdf_url":"https://arxiv.org/pdf/2105.08970","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.08970","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.08970","pdf_url":"https://arxiv.org/pdf/2105.08970","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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2039844283","https://openalex.org/W2051428568","https://openalex.org/W2091270830","https://openalex.org/W2108501770","https://openalex.org/W2135284480","https://openalex.org/W2149273154","https://openalex.org/W2516001803","https://openalex.org/W2621350877","https://openalex.org/W2621357189","https://openalex.org/W2747876639","https://openalex.org/W2753738274","https://openalex.org/W2766672686","https://openalex.org/W2769521316","https://openalex.org/W2785519580","https://openalex.org/W2883322837","https://openalex.org/W2892845759","https://openalex.org/W2917987043","https://openalex.org/W2918296821","https://openalex.org/W2942718970","https://openalex.org/W2948978827","https://openalex.org/W2963104724","https://openalex.org/W2963264829","https://openalex.org/W2963375116","https://openalex.org/W2963504544","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W2964127395","https://openalex.org/W2996554397","https://openalex.org/W3097549261","https://openalex.org/W3097756030","https://openalex.org/W3100968126","https://openalex.org/W3103543904","https://openalex.org/W3114440105","https://openalex.org/W3130335839","https://openalex.org/W3131332223","https://openalex.org/W4289129346","https://openalex.org/W6631190155","https://openalex.org/W6675944832","https://openalex.org/W6738835615","https://openalex.org/W6739139180","https://openalex.org/W6748223763","https://openalex.org/W6748391871","https://openalex.org/W6762464624","https://openalex.org/W6790869478"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Recently,":[0],"the":[1,53,62,74,94,97,110,113,125,128,131,144,147],"standard":[2,75],"variational":[3,76,90,114,132],"autoencoder":[4],"has":[5],"been":[6,29],"successfully":[7],"used":[8,20,161],"to":[9,21,58,73,83,92,136,139],"learn":[10,140],"a":[11,32,35,45,105,152],"probabilistic":[12],"prior":[13],"over":[14],"speech":[15,23,37,40,50,163],"signals,":[16],"which":[17,66,134],"is":[18,55,160],"then":[19,28],"perform":[22],"enhancement.":[24,164],"Variational":[25],"autoen-coders":[26],"have":[27],"conditioned":[30],"on":[31],"label":[33,54,95,126],"describing":[34],"high-level":[36],"attribute":[38],"(e.g.":[39],"activity)":[41],"that":[42,107,123],"allows":[43],"for":[44,89,127,162],"more":[46],"explicit":[47],"control":[48],"of":[49,112,130,146],"generation.":[51],"However,":[52],"not":[56],"guaranteed":[57],"be":[59,137],"disentangled":[60],"from":[61,96,157],"other":[63,98],"latent":[64,99],"variables,":[65],"results":[67],"in":[68],"limited":[69],"performance":[70],"improvements":[71],"compared":[72],"autoencoder.":[77,115],"In":[78],"this":[79],"work,":[80],"we":[81,103,117],"propose":[82],"use":[84,104,119],"an":[85,120],"adversarial":[86],"training":[87],"scheme":[88],"autoencoders":[91],"disentangle":[93],"variables.":[100],"At":[101],"training,":[102],"discriminator":[106],"competes":[108],"with":[109],"encoder":[111,122],"Simultaneously\u2019":[116],"also":[118],"additional":[121],"estimates":[124],"decoder":[129],"autoencoder,":[133],"proves":[135],"crucial":[138],"disentanglement.":[141],"We":[142],"show":[143],"benefit":[145],"proposed":[148],"disentanglement":[149],"learning":[150],"when":[151],"voice":[153],"activity":[154],"label,":[155],"estimated":[156],"visual":[158],"data,":[159]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}