{"id":"https://openalex.org/W3049360585","doi":"https://doi.org/10.1109/mlsp52302.2021.9596406","title":"Deep Variational Generative Models for Audio-Visual Speech Separation","display_name":"Deep Variational Generative Models for Audio-Visual Speech Separation","publication_year":2021,"publication_date":"2021-10-25","ids":{"openalex":"https://openalex.org/W3049360585","doi":"https://doi.org/10.1109/mlsp52302.2021.9596406","mag":"3049360585"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp52302.2021.9596406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","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/2008.07191","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085659980","display_name":"Viet-Nhat Nguyen","orcid":null},"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":"Viet-Nhat Nguyen","raw_affiliation_strings":["RobotLearn Team at Inria Grenoble Rhône-Alpes,France","RobotLearn Team at Inria Grenoble Rh\u00f4ne-Alpes,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RobotLearn Team at Inria Grenoble Rhône-Alpes,France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"RobotLearn Team at Inria Grenoble Rh\u00f4ne-Alpes,France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348","https://openalex.org/I899635006"]}]},{"author_position":"middle","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":["RobotLearn Team at Inria Grenoble Rhône-Alpes,France","RobotLearn Team at Inria Grenoble Rh\u00f4ne-Alpes,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RobotLearn Team at Inria Grenoble Rhône-Alpes,France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"RobotLearn Team at Inria Grenoble Rh\u00f4ne-Alpes,France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348","https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065059558","display_name":"Elisa Ricci","orcid":"https://orcid.org/0000-0002-0228-1147"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elisa Ricci","raw_affiliation_strings":["Università degli Studi di Trento,Italy","Universit\u00e0 Degli Studi di Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Università degli Studi di Trento,Italy","institution_ids":["https://openalex.org/I193223587"]},{"raw_affiliation_string":"Universit\u00e0 Degli Studi di Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"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":["RobotLearn Team at Inria Grenoble Rhône-Alpes,France","RobotLearn Team at Inria Grenoble Rh\u00f4ne-Alpes,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RobotLearn Team at Inria Grenoble Rhône-Alpes,France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"RobotLearn Team at Inria Grenoble Rh\u00f4ne-Alpes,France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348","https://openalex.org/I899635006"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"1","last_page":"6"},"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":0.9987000226974487,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7560676336288452},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.7050117254257202},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6468957662582397},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.6337924003601074},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6027525663375854},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.565716564655304},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5656048059463501},{"id":"https://openalex.org/keywords/latent-variable-model","display_name":"Latent variable model","score":0.47850266098976135},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.46924924850463867},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4383329451084137},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4173282980918884},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.41707417368888855},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40258845686912537},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3349592089653015},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3219575881958008},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.208444744348526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7560676336288452},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.7050117254257202},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6468957662582397},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.6337924003601074},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6027525663375854},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.565716564655304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5656048059463501},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.47850266098976135},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.46924924850463867},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4383329451084137},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4173282980918884},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.41707417368888855},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40258845686912537},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3349592089653015},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3219575881958008},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.208444744348526},{"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/mlsp52302.2021.9596406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.07191","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.07191","pdf_url":"https://arxiv.org/pdf/2008.07191","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":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-02930662v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-02930662","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MLSP 2021 - IEEE International Workshop on Machine Learning for Signal Processing, Oct 2021, Gold Coast, Australia. pp.1-6, ⟨10.1109/MLSP52302.2021.9596406⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2008.07191","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.07191","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.07191","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.07191","pdf_url":"https://arxiv.org/pdf/2008.07191","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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.75,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"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/G2092057362","display_name":null,"funder_award_id":"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"},{"id":"https://openalex.org/G8318455765","display_name":null,"funder_award_id":"ANR-19","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3049360585.pdf","grobid_xml":"https://content.openalex.org/works/W3049360585.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2029199293","https://openalex.org/W2067295501","https://openalex.org/W2127851351","https://openalex.org/W2135029798","https://openalex.org/W2138309709","https://openalex.org/W2143169494","https://openalex.org/W2160813409","https://openalex.org/W2188365844","https://openalex.org/W2766672686","https://openalex.org/W2783473931","https://openalex.org/W2883322837","https://openalex.org/W2900292050","https://openalex.org/W2963082324","https://openalex.org/W2964121744","https://openalex.org/W2965390715","https://openalex.org/W3015791137","https://openalex.org/W3123318516","https://openalex.org/W3137758952","https://openalex.org/W3182657421","https://openalex.org/W3209141406","https://openalex.org/W4289665794","https://openalex.org/W6631190155","https://openalex.org/W6680012447","https://openalex.org/W6683557349","https://openalex.org/W6687045409"],"related_works":["https://openalex.org/W3213412873","https://openalex.org/W3137758952","https://openalex.org/W2982264772","https://openalex.org/W2785390226","https://openalex.org/W2109087058","https://openalex.org/W3094247854","https://openalex.org/W2102863932","https://openalex.org/W3130335839","https://openalex.org/W2105055531","https://openalex.org/W3023996010","https://openalex.org/W2897548994","https://openalex.org/W3125709657","https://openalex.org/W2087368178","https://openalex.org/W3121737235","https://openalex.org/W3131643166","https://openalex.org/W2403836935","https://openalex.org/W3096474940","https://openalex.org/W2010284423","https://openalex.org/W2126245649","https://openalex.org/W2140899792"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"are":[4,71,135],"interested":[5],"in":[6],"audio-visual":[7,33],"speech":[8,52,75],"separation":[9,155],"given":[10],"a":[11,43,55,92,98,139,163],"single-channel":[12],"audio":[13],"recording":[14],"as":[15,17,80,82,91,160,162],"well":[16,81,161],"visual":[18,63,84,87,99],"information":[19],"(lips":[20],"movements)":[21],"associated":[22],"with":[23,116],"each":[24],"speaker.":[25],"We":[26],"propose":[27],"an":[28,117],"unsupervised":[29,118,150],"technique":[30],"based":[31],"on":[32],"generative":[34,46,106],"modeling":[35],"of":[36,67,77],"clean":[37,51,78],"speech.":[38],"More":[39],"specifically,":[40],"during":[41],"training,":[42],"latent":[44,69,95,130],"variable":[45],"model":[47,107,124],"is":[48,114],"learned":[49,105],"from":[50,73],"spectra":[53],"using":[54],"variational":[56],"auto-encoder":[57],"(VAE).":[58],"To":[59],"better":[60,154],"utilize":[61],"the":[62,65,68,83,104,129,148],"information,":[64],"posteriors":[66],"variables":[70,131],"inferred":[72],"mixed":[74],"(instead":[76],"speech)":[79],"data.":[85],"The":[86],"modality":[88],"also":[89],"serves":[90],"prior":[93],"for":[94,109,125],"variables,":[96],"through":[97],"network.":[100],"At":[101],"test":[102],"time,":[103],"(both":[108],"speaker-independent":[110],"and":[111,132],"speaker-dependent":[112],"scenarios)":[113],"combined":[115],"non-negative":[119],"matrix":[120],"factorization":[121],"(NMF)":[122],"variance":[123],"background":[126],"noise.":[127],"All":[128],"noise":[133],"parameters":[134],"then":[136],"estimated":[137],"by":[138],"Monte":[140],"Carlo":[141],"expectation-maximization":[142],"algorithm.":[143],"Our":[144],"experiments":[145],"show":[146],"that":[147],"proposed":[149],"VAE-based":[151],"method":[152],"yields":[153],"performance":[156],"than":[157],"NMF-based":[158],"approaches":[159],"supervised":[164],"deep":[165],"learning-based":[166],"technique.":[167]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-08-21T00:00:00"}