{"id":"https://openalex.org/W2983444678","doi":"https://doi.org/10.1109/icassp40776.2020.9053730","title":"Robust Unsupervised Audio-Visual Speech Enhancement Using a Mixture of Variational Autoencoders","display_name":"Robust Unsupervised Audio-Visual Speech Enhancement Using a Mixture of Variational Autoencoders","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2983444678","doi":"https://doi.org/10.1109/icassp40776.2020.9053730","mag":"2983444678"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.03930","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001931776","display_name":"Mostafa Sadeghi","orcid":"https://orcid.org/0000-0002-3493-3517"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"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, France","INRIA Grenoble \u2010 Rh\u00f4ne\u2010Alpes France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria Grenoble Rh\u00f4ne-Alpes, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348","https://openalex.org/I899635006"]},{"raw_affiliation_string":"INRIA Grenoble \u2010 Rh\u00f4ne\u2010Alpes France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066621495","display_name":"Xavier Alameda-Pineda","orcid":"https://orcid.org/0000-0002-5354-1084"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"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, France","INRIA Grenoble \u2010 Rh\u00f4ne\u2010Alpes France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria Grenoble Rh\u00f4ne-Alpes, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348","https://openalex.org/I899635006"]},{"raw_affiliation_string":"INRIA Grenoble \u2010 Rh\u00f4ne\u2010Alpes France","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7534","last_page":"7538"},"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":0.9865999817848206,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9814000129699707,"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/autoencoder","display_name":"Autoencoder","score":0.7901523113250732},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7807367444038391},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6811709403991699},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.6695659160614014},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.651308536529541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6262810826301575},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5040799379348755},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4904477298259735},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4728800654411316},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.44084253907203674},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4388103187084198},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.28538191318511963},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.23167771100997925},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1326141655445099}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7901523113250732},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7807367444038391},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6811709403991699},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.6695659160614014},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.651308536529541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6262810826301575},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5040799379348755},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4904477298259735},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4728800654411316},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.44084253907203674},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4388103187084198},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.28538191318511963},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.23167771100997925},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1326141655445099},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.03930","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.03930","pdf_url":"https://arxiv.org/pdf/1911.03930","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-02534911v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02534911","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":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2020, Barcelona, Spain. pp.7534-7538, ⟨10.1109/ICASSP40776.2020.9053730⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.1911.03930","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.03930","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/srpa-hh29","is_oa":true,"landing_page_url":"https://doi.org/10.17023/srpa-hh29","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"},{"id":"mag:2983444678","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.03930","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.03930","pdf_url":"https://arxiv.org/pdf/1911.03930","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5799999833106995}],"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/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":26,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W1663973292","https://openalex.org/W1959608418","https://openalex.org/W2038010270","https://openalex.org/W2039844283","https://openalex.org/W2044893557","https://openalex.org/W2127851351","https://openalex.org/W2747876639","https://openalex.org/W2766672686","https://openalex.org/W2883322837","https://openalex.org/W2901552243","https://openalex.org/W2911579794","https://openalex.org/W2918296821","https://openalex.org/W2922004249","https://openalex.org/W2943237054","https://openalex.org/W2962866211","https://openalex.org/W2963082324","https://openalex.org/W2964171275","https://openalex.org/W2965390715","https://openalex.org/W2972516210","https://openalex.org/W3100968126","https://openalex.org/W4245919820","https://openalex.org/W6633117090","https://openalex.org/W6640963894","https://openalex.org/W6840371246"],"related_works":["https://openalex.org/W3015791137","https://openalex.org/W2965390715","https://openalex.org/W3004146833","https://openalex.org/W2959214850","https://openalex.org/W1869491686","https://openalex.org/W2788241093","https://openalex.org/W3109940347","https://openalex.org/W2278884322","https://openalex.org/W2396163457","https://openalex.org/W2064347532","https://openalex.org/W2958646611","https://openalex.org/W3025878903","https://openalex.org/W172154728","https://openalex.org/W3137787835","https://openalex.org/W2051360208","https://openalex.org/W2752520680","https://openalex.org/W182561118","https://openalex.org/W2063425879","https://openalex.org/W2112348857","https://openalex.org/W2042419400"],"abstract_inverted_index":{"Recently,":[0],"an":[1],"audio-visual":[2,40,57,90,113],"speech":[3,30,37,91],"generative":[4],"model":[5,23,103],"based":[6,94],"on":[7,53,95],"variational":[8,133],"autoencoder":[9],"(VAE)":[10],"has":[11],"been":[12],"proposed,":[13],"which":[14,50],"is":[15,35,51,59,74,80,117],"combined":[16],"with":[17,39,47],"a":[18,43,87,96,106,111,132],"nonnegative":[19],"matrix":[20],"factorization":[21],"(NMF)":[22],"for":[24,68],"noise":[25],"variance":[26],"to":[27,118,125,136],"perform":[28],"unsupervised":[29,89],"enhancement.":[31],"When":[32],"visual":[33,64,121],"data":[34],"clean,":[36],"enhancement":[38,92],"VAE":[41,58,98,109,128],"shows":[42],"better":[44],"performance":[45,147],"than":[46],"audio-only":[48,54,108,127],"VAE,":[49],"trained":[52,107,112],"data.":[55],"However,":[56],"not":[60,75],"robust":[61,88],"against":[62],"noisy":[63,120],"data,":[65],"e.g.,":[66],"when":[67],"some":[69],"video":[70],"frames,":[71],"speaker":[72],"face":[73],"frontal":[76],"or":[77],"lips":[78],"region":[79],"occluded.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85],"propose":[86],"method":[93,135],"per-frame":[97],"mixture":[99,102],"model.":[100,129,142],"This":[101],"consists":[104],"of":[105,140,148],"and":[110],"VAE.":[114],"The":[115],"motivation":[116],"skip":[119],"frames":[122],"by":[123],"switching":[124],"the":[126,138,141,145,149],"We":[130],"present":[131],"expectation-maximization":[134],"estimate":[137],"parameters":[139],"Experiments":[143],"show":[144],"promising":[146],"proposed":[150],"method.":[151]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}