{"id":"https://openalex.org/W3127489130","doi":"https://doi.org/10.1109/icassp39728.2021.9414097","title":"Switching Variational Auto-Encoders for Noise-Agnostic Audio-Visual Speech Enhancement","display_name":"Switching Variational Auto-Encoders for Noise-Agnostic Audio-Visual Speech Enhancement","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3127489130","doi":"https://doi.org/10.1109/icassp39728.2021.9414097","mag":"3127489130"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/2102.04144","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/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/I4210127166","display_name":"Centre Inria de l'Universit\u00e9 de Lorraine","ror":"https://ror.org/03fcjvn64","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210127166"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mostafa Sadeghi","raw_affiliation_strings":["Inria Nancy Grand-Est","INRIA Nancy Grand Est"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria Nancy Grand-Est","institution_ids":["https://openalex.org/I4210127166"]},{"raw_affiliation_string":"INRIA Nancy Grand Est","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210127166"]}]},{"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 Rhone-Alpes & Univ. Grenoble Alpes, France","INRIA Grenoble Rh\u00f4ne-Alpes & Univ. Grenoble Alpes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria Grenoble Rhone-Alpes & Univ. Grenoble Alpes, France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I899635006"]},{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes & Univ. Grenoble Alpes, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I899635006"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6663","last_page":"6667"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9918000102043152,"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/computer-science","display_name":"Computer science","score":0.7657126188278198},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.6043911576271057},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5355225801467896},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5279352068901062},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5199174284934998},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5005466938018799},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4842185974121094},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4317636489868164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4238140881061554},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.394700288772583},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3844676911830902},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3211114704608917},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.276073157787323},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20255222916603088},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1936173141002655},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.18849709630012512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657126188278198},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.6043911576271057},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5355225801467896},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5279352068901062},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5199174284934998},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5005466938018799},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4842185974121094},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4317636489868164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4238140881061554},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.394700288772583},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3844676911830902},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3211114704608917},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.276073157787323},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20255222916603088},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1936173141002655},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.18849709630012512},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.04144","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.04144","pdf_url":"https://arxiv.org/pdf/2102.04144","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":"mag:3127489130","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.04144.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":"pmh:oai:HAL:hal-03155445v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03155445","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":"https://www.2021.ieeeicassp.org/","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2102.04144","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.04144","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/x6d1-7x42","is_oa":true,"landing_page_url":"https://doi.org/10.17023/x6d1-7x42","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.04144","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.04144","pdf_url":"https://arxiv.org/pdf/2102.04144","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":0.7099999785423279}],"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":30,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1663973292","https://openalex.org/W1959608418","https://openalex.org/W2038010270","https://openalex.org/W2039844283","https://openalex.org/W2054852564","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2747876639","https://openalex.org/W2752604219","https://openalex.org/W2766672686","https://openalex.org/W2788241093","https://openalex.org/W2963082324","https://openalex.org/W2964121744","https://openalex.org/W2964171275","https://openalex.org/W2965390715","https://openalex.org/W2972513594","https://openalex.org/W2996743179","https://openalex.org/W3015791137","https://openalex.org/W3081461879","https://openalex.org/W3082851515","https://openalex.org/W3100968126","https://openalex.org/W6631190155","https://openalex.org/W6633117090","https://openalex.org/W6640963894","https://openalex.org/W6769644785","https://openalex.org/W6772200532","https://openalex.org/W6782486312","https://openalex.org/W6783123723","https://openalex.org/W6785473800"],"related_works":["https://openalex.org/W3160658686","https://openalex.org/W3211665488","https://openalex.org/W3031135612","https://openalex.org/W2132423630","https://openalex.org/W2724603107","https://openalex.org/W2946555236","https://openalex.org/W3091830790","https://openalex.org/W2797972631","https://openalex.org/W2738829871","https://openalex.org/W2601064856","https://openalex.org/W2887264325","https://openalex.org/W1591308582","https://openalex.org/W3091539257","https://openalex.org/W3181138750","https://openalex.org/W2288648150","https://openalex.org/W3114957460","https://openalex.org/W2242670557","https://openalex.org/W1676004188","https://openalex.org/W2290318471","https://openalex.org/W3016169273"],"abstract_inverted_index":{"Recently,":[0],"audio-visual":[1,67],"speech":[2,171],"enhancement":[3],"has":[4],"been":[5],"tackled":[6],"in":[7,131],"the":[8,53,59,72,79,87,91,100,113,148,156,163,166,170,176],"unsupervised":[9,133],"settings":[10],"based":[11],"on":[12],"variational":[13,138,144,158],"auto-encoders":[14],"(VAEs),":[15],"where":[16],"during":[17],"training":[18],"only":[19],"clean":[20],"data":[21,64,81],"is":[22,35,56],"used":[23],"to":[24,58,98,123,136,146,161],"train":[25],"a":[26,38,116,143],"generative":[27],"model":[28,55,167],"for":[29],"speech,":[30],"which":[31],"at":[32],"test":[33],"time":[34,130],"combined":[36],"with":[37,120],"noise":[39,60],"model,":[40],"e.g.":[41,86],"nonnegative":[42],"matrix":[43],"factorization":[44,145],"(NMF),":[45],"whose":[46],"parameters":[47,164],"are":[48,65,82],"learned":[49],"without":[50],"supervision.":[51],"Consequently,":[52],"proposed":[54],"agnostic":[57],"type.":[61],"When":[62],"visual":[63,80],"clean,":[66],"VAE-based":[68],"architectures":[69,106,128],"usually":[70],"outperform":[71],"audio-only":[73],"counterpart.":[74],"The":[75],"opposite":[76],"happens":[77],"when":[78],"corrupted":[83],"by":[84],"clutter,":[85],"speaker":[88],"not":[89],"facing":[90],"camera.":[92],"In":[93],"this":[94],"paper,":[95],"we":[96,111],"propose":[97,142],"find":[99],"optimal":[101],"combination":[102],"of":[103,115,165,179],"these":[104],"two":[105],"through":[107,129],"time.":[108],"More":[109],"precisely,":[110],"introduce":[112],"use":[114],"latent":[117],"sequential":[118],"variable":[119],"Markovian":[121],"dependencies":[122],"switch":[124],"between":[125],"different":[126],"VAE":[127],"an":[132],"manner:":[134],"leading":[135],"switching":[137],"auto-encoder":[139],"(SwVAE).":[140],"We":[141,153],"approximate":[147],"computationally":[149],"intractable":[150],"posterior":[151],"distribution.":[152],"also":[154],"derive":[155],"corresponding":[157],"expectation-maximization":[159],"algorithm":[160],"estimate":[162],"and":[168],"enhance":[169],"signal.":[172],"Our":[173],"experiments":[174],"demonstrate":[175],"promising":[177],"performance":[178],"SwVAE.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}