{"id":"https://openalex.org/W2965390715","doi":"https://doi.org/10.1109/taslp.2020.3000593","title":"Audio-Visual Speech Enhancement Using Conditional Variational Auto-Encoders","display_name":"Audio-Visual Speech Enhancement Using Conditional Variational Auto-Encoders","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W2965390715","doi":"https://doi.org/10.1109/taslp.2020.3000593","mag":"2965390715"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3000593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3000593","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1908.02590","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062612015","display_name":"Mostafa Sadeghi","orcid":"https://orcid.org/0000-0002-0272-8017"},"institutions":[{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mostafa Sadeghi","raw_affiliation_strings":["Inria Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","University Grenoble Alpes, Grenoble, France"],"raw_orcid":"https://orcid.org/0000-0002-0272-8017","affiliations":[{"raw_affiliation_string":"Inria Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I899635006"]},{"raw_affiliation_string":"University Grenoble Alpes, Grenoble, France","institution_ids":["https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045593473","display_name":"Simon Leglaive","orcid":"https://orcid.org/0000-0002-8219-1298"},"institutions":[{"id":"https://openalex.org/I4210100151","display_name":"Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique","ror":"https://ror.org/013q33h79","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210095849","https://openalex.org/I4210100151","https://openalex.org/I56067802","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Simon Leglaive","raw_affiliation_strings":["CentraleSup\u00e9lec, IETR, Cesson Sevigne, France","Inria Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France"],"raw_orcid":"https://orcid.org/0000-0002-8219-1298","affiliations":[{"raw_affiliation_string":"CentraleSup\u00e9lec, IETR, Cesson Sevigne, France","institution_ids":["https://openalex.org/I4210100151","https://openalex.org/I4210107720"]},{"raw_affiliation_string":"Inria Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066621495","display_name":"Xavier Alameda-Pineda","orcid":"https://orcid.org/0000-0002-5354-1084"},"institutions":[{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xavier Alameda-Pineda","raw_affiliation_strings":["Inria Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","University Grenoble Alpes, Grenoble, France"],"raw_orcid":"https://orcid.org/0000-0002-5354-1084","affiliations":[{"raw_affiliation_string":"Inria Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I899635006"]},{"raw_affiliation_string":"University Grenoble Alpes, Grenoble, France","institution_ids":["https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020392160","display_name":"Laurent Girin","orcid":"https://orcid.org/0000-0002-9214-8760"},"institutions":[{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Girin","raw_affiliation_strings":["GIPSA-Lab, University Grenoble Alpes, Grenoble, France","Inria Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","University Grenoble Alpes, Grenoble, France"],"raw_orcid":"https://orcid.org/0000-0002-9214-8760","affiliations":[{"raw_affiliation_string":"GIPSA-Lab, University Grenoble Alpes, Grenoble, France","institution_ids":["https://openalex.org/I4210124956","https://openalex.org/I899635006"]},{"raw_affiliation_string":"Inria Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I899635006"]},{"raw_affiliation_string":"University Grenoble Alpes, Grenoble, France","institution_ids":["https://openalex.org/I899635006"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078307335","display_name":"Radu Horaud","orcid":"https://orcid.org/0000-0001-5232-024X"},"institutions":[{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Radu Horaud","raw_affiliation_strings":["Inria Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","University Grenoble Alpes, Grenoble, France"],"raw_orcid":"https://orcid.org/0000-0001-5232-024X","affiliations":[{"raw_affiliation_string":"Inria Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I899635006"]},{"raw_affiliation_string":"University Grenoble Alpes, Grenoble, France","institution_ids":["https://openalex.org/I899635006"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.8242,"has_fulltext":false,"cited_by_count":81,"citation_normalized_percentile":{"value":0.97688785,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"28","issue":null,"first_page":"1788","last_page":"1800"},"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":0.9972000122070312,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9932000041007996,"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/computer-science","display_name":"Computer science","score":0.7878819704055786},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6905101537704468},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6424064040184021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5402209162712097},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5183935761451721},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.49860644340515137},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.488565057516098},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.41208580136299133},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.41010138392448425},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3865438401699066},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3512765169143677},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34126192331314087},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.32928746938705444},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2531434893608093},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1110149621963501}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878819704055786},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6905101537704468},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6424064040184021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5402209162712097},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5183935761451721},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.49860644340515137},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.488565057516098},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.41208580136299133},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.41010138392448425},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3865438401699066},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3512765169143677},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34126192331314087},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.32928746938705444},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2531434893608093},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1110149621963501}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2020.3000593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3000593","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1908.02590","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.02590","pdf_url":"https://arxiv.org/pdf/1908.02590","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"},{"id":"pmh:oai:HAL:hal-02364900v2","is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-02364900","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 2329-9290","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:HAL:hal-02364900v3","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02364900","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 2020, 28, pp.1788-1800. &#x27E8;10.1109/TASLP.2020.3000593&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1908.02590","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.02590","pdf_url":"https://arxiv.org/pdf/1908.02590","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6100000143051147}],"awards":[{"id":"https://openalex.org/G1041279674","display_name":"MIAI @ Grenoble Alpes","funder_award_id":"ANR-19-P3IA-0003","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G1464039697","display_name":"NExT (I-SITE)","funder_award_id":"ANR-16-IDEX-0007","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5495492380","display_name":"Multi-Modal Multi-person Low-Level Learning for Robot Interaction","funder_award_id":"ANR-19-CE33-0008","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":87,"referenced_works":["https://openalex.org/W1488856050","https://openalex.org/W1495679096","https://openalex.org/W1504438288","https://openalex.org/W1516111018","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1573024203","https://openalex.org/W1897240248","https://openalex.org/W1968939597","https://openalex.org/W1969975883","https://openalex.org/W1983108229","https://openalex.org/W1985093013","https://openalex.org/W1991893000","https://openalex.org/W2002621203","https://openalex.org/W2013608223","https://openalex.org/W2014621385","https://openalex.org/W2015143272","https://openalex.org/W2038010270","https://openalex.org/W2039844283","https://openalex.org/W2044893557","https://openalex.org/W2049633694","https://openalex.org/W2069681747","https://openalex.org/W2072634211","https://openalex.org/W2099128937","https://openalex.org/W2106488367","https://openalex.org/W2108501770","https://openalex.org/W2109215269","https://openalex.org/W2114508388","https://openalex.org/W2115109087","https://openalex.org/W2121973264","https://openalex.org/W2126942983","https://openalex.org/W2127851351","https://openalex.org/W2128653836","https://openalex.org/W2137400100","https://openalex.org/W2141998673","https://openalex.org/W2147299274","https://openalex.org/W2158291955","https://openalex.org/W2168379380","https://openalex.org/W2188365844","https://openalex.org/W2225156818","https://openalex.org/W2278884322","https://openalex.org/W2395107641","https://openalex.org/W2405774341","https://openalex.org/W2516342150","https://openalex.org/W2747876639","https://openalex.org/W2750143381","https://openalex.org/W2753738274","https://openalex.org/W2766672686","https://openalex.org/W2788241093","https://openalex.org/W2804690068","https://openalex.org/W2883322837","https://openalex.org/W2886232760","https://openalex.org/W2901552243","https://openalex.org/W2905196628","https://openalex.org/W2911579794","https://openalex.org/W2922004249","https://openalex.org/W2922391058","https://openalex.org/W2936446744","https://openalex.org/W2943237054","https://openalex.org/W2949416428","https://openalex.org/W2962866211","https://openalex.org/W2963082324","https://openalex.org/W2963375116","https://openalex.org/W2963654155","https://openalex.org/W2964121744","https://openalex.org/W2964171275","https://openalex.org/W2972516210","https://openalex.org/W2975955714","https://openalex.org/W2991015288","https://openalex.org/W3100968126","https://openalex.org/W3101380508","https://openalex.org/W3127686677","https://openalex.org/W3147539069","https://openalex.org/W4232282348","https://openalex.org/W4245883374","https://openalex.org/W4245919820","https://openalex.org/W4292691288","https://openalex.org/W6629442188","https://openalex.org/W6631190155","https://openalex.org/W6675117242","https://openalex.org/W6675944832","https://openalex.org/W6687045409","https://openalex.org/W6694617781","https://openalex.org/W6712351927","https://openalex.org/W6713658392","https://openalex.org/W6743691625","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W4375869169","https://openalex.org/W2597829360","https://openalex.org/W2921661700","https://openalex.org/W2138406058","https://openalex.org/W2153897396","https://openalex.org/W2157102033","https://openalex.org/W3096964161","https://openalex.org/W2131486661","https://openalex.org/W2005805562","https://openalex.org/W2115778783"],"abstract_inverted_index":{"Variational":[0],"auto-encoders":[1],"(VAEs)":[2],"are":[3,128],"deep":[4,194],"generative":[5,45,87,104],"latent":[6],"variable":[7],"models":[8],"that":[9,48,145,182],"can":[10],"be":[11],"used":[12,24,36],"for":[13,71],"learning":[14,195],"the":[15,84,95,101,131,139,146,159,165,171,183],"distribution":[16],"of":[17,43,54,69,94],"complex":[18],"data.":[19],"VAEs":[20,70],"have":[21],"been":[22],"successfully":[23],"to":[25,37],"learn":[26],"a":[27,79,109,122,191],"probabilistic":[28],"prior":[29],"over":[30],"speech":[31,39,58,75,86,103,118,160,172,187],"signals,":[32],"which":[33],"is":[34,47,89,106,174],"then":[35],"perform":[38],"enhancement.":[40,76],"One":[41],"advantage":[42],"this":[44,63],"approach":[46,189],"it":[49,157],"does":[50],"not":[51],"require":[52],"pairs":[53],"clean":[55],"and":[56,73,117,153,156],"noisy":[57],"signals":[59],"at":[60],"training.":[61],"In":[62],"article,":[64],"we":[65],"propose":[66],"audio-visual":[67,102,148,186],"variants":[68],"single-channel":[72],"speaker-independent":[74],"We":[77,179],"develop":[78],"conditional":[80],"VAE":[81,167],"(CVAE)":[82],"where":[83],"audio":[85,152],"process":[88],"conditioned":[90],"on":[91,113,121],"visual":[92,154],"information":[93],"lip":[96],"region.":[97],"At":[98],"test":[99],"time,":[100],"model":[105,111],"combined":[107],"with":[108,130,164],"noise":[110],"based":[112],"nonnegative":[114],"matrix":[115],"factorization,":[116],"enhancement":[119,161,188],"relies":[120],"Monte":[123],"Carlo":[124],"expectation-maximization":[125],"algorithm.":[126],"Experiments":[127],"conducted":[129],"recently":[132],"published":[133],"NTCD-TIMIT":[134],"dataset":[135],"as":[136,138],"well":[137],"GRID":[140],"corpus.":[141],"The":[142],"results":[143],"confirm":[144],"proposed":[147,184],"CVAE":[149],"effectively":[150],"fuses":[151],"information,":[155],"improves":[158],"performance":[162],"compared":[163],"audio-only":[166],"model,":[168],"especially":[169],"when":[170],"signal":[173],"highly":[175],"corrupted":[176],"by":[177],"noise.":[178],"also":[180],"show":[181],"unsupervised":[185],"outperforms":[190],"state-of-the-art":[192],"supervised":[193],"method.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
