{"id":"https://openalex.org/W4403116286","doi":"https://doi.org/10.1109/icassp49660.2025.10887628","title":"Diffusion-based Unsupervised Audio-visual Speech Enhancement","display_name":"Diffusion-based Unsupervised Audio-visual Speech Enhancement","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4403116286","doi":"https://doi.org/10.1109/icassp49660.2025.10887628"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.05301","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092912265","display_name":"Jean-Eudes Ayilo","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Eudes Ayilo","raw_affiliation_strings":["Université de Lorraine,CNRS, Inria, Loria,Nancy,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine,CNRS, Inria, Loria,Nancy,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062612015","display_name":"Mostafa Sadeghi","orcid":"https://orcid.org/0000-0002-0272-8017"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mostafa Sadeghi","raw_affiliation_strings":["Université de Lorraine,CNRS, Inria, Loria,Nancy,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine,CNRS, Inria, Loria,Nancy,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Romain Serizel","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Romain Serizel","raw_affiliation_strings":["Université de Lorraine,CNRS, Inria, Loria,Nancy,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine,CNRS, Inria, Loria,Nancy,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838"]}]},{"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/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":["Université Grenoble Alpes,Inria,Grenoble,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Grenoble Alpes,Inria,Grenoble,France","institution_ids":["https://openalex.org/I4210101348","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":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9714000225067139,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9419999718666077,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8095626831054688},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.7863651514053345},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6445742845535278},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6281367540359497},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5968687534332275},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5879853963851929},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.575667679309845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5035094618797302},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.453754186630249},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4363098442554474},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.42119094729423523},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.41628536581993103},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4070794880390167},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38006123900413513},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.27278971672058105},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16765207052230835},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13232016563415527},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12619885802268982}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8095626831054688},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.7863651514053345},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6445742845535278},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6281367540359497},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5968687534332275},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5879853963851929},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.575667679309845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5035094618797302},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.453754186630249},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4363098442554474},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.42119094729423523},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41628536581993103},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4070794880390167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38006123900413513},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.27278971672058105},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16765207052230835},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13232016563415527},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12619885802268982},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.05301","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.05301","pdf_url":"https://arxiv.org/pdf/2410.05301","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-04718254v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04718254","pdf_url":"https://hal.science/hal-04718254v1/document","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":"International Conference on Acoustics Speech and Signal Processing (ICASSP), IEEE, Apr 2025, Hyderabad, India","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.05301","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.05301","pdf_url":"https://arxiv.org/pdf/2410.05301","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":[],"awards":[{"id":"https://openalex.org/G1102524033","display_name":"Robust and Efficient Deep Learning based Audiovisual Speech Enhancement","funder_award_id":"ANR-22-CE23-0026","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403116286.pdf","grobid_xml":"https://content.openalex.org/works/W4403116286.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1991111872","https://openalex.org/W2014621385","https://openalex.org/W2015394094","https://openalex.org/W2015810892","https://openalex.org/W2029199293","https://openalex.org/W2516001803","https://openalex.org/W2747876639","https://openalex.org/W2788241093","https://openalex.org/W2963341071","https://openalex.org/W2964058413","https://openalex.org/W2964171275","https://openalex.org/W2965390715","https://openalex.org/W2972513594","https://openalex.org/W3136499730","https://openalex.org/W3160567113","https://openalex.org/W3174264304","https://openalex.org/W4214567298","https://openalex.org/W4221144097","https://openalex.org/W4232282348","https://openalex.org/W4281820413","https://openalex.org/W4307286264","https://openalex.org/W4311841164","https://openalex.org/W4319862437","https://openalex.org/W4375869120","https://openalex.org/W4380434618","https://openalex.org/W4380715308","https://openalex.org/W4385478414","https://openalex.org/W4392903364","https://openalex.org/W4392904258","https://openalex.org/W4392910516","https://openalex.org/W4399554121","https://openalex.org/W4402112025","https://openalex.org/W6680012447","https://openalex.org/W6754420807","https://openalex.org/W6786375611","https://openalex.org/W6810168380","https://openalex.org/W6851069163","https://openalex.org/W6853966563"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W34555840"],"abstract_inverted_index":{"This":[0,47],"paper":[1],"proposes":[2],"a":[3,13,20,64,80,111,122],"new":[4,118],"unsupervised":[5],"audiovisual":[6],"speech":[7,16,35,44,61,81],"enhancement":[8],"(AVSE)":[9],"approach":[10,68,99],"that":[11,95],"combines":[12],"diffusion-based":[14,65,134],"audio-visual":[15],"generative":[17,45],"model":[18,30,49,57],"with":[19,53],"non-negative":[21],"matrix":[22],"factorization":[23],"(NMF)":[24],"noise":[25,56,90],"model.":[26],"First,":[27],"the":[28,43,54,72,89,96,117,132],"diffusion":[29,74],"is":[31,50,69,83],"pre-trained":[32,48],"on":[33,37],"clean":[34,60],"conditioned":[36],"corresponding":[38],"video":[39],"data":[40],"to":[41,58,87,131],"simulate":[42],"distribution.":[46],"then":[51],"paired":[52],"NMF-based":[55],"estimate":[59,82],"iteratively.":[62],"Specifically,":[63],"posterior":[66],"sampling":[67],"implemented":[70],"within":[71],"reverse":[73],"process,":[75],"where":[76],"after":[77],"each":[78],"iteration,":[79],"obtained":[84],"and":[85,128,137],"used":[86],"update":[88],"parameters.":[91],"Experimental":[92],"results":[93],"confirm":[94],"proposed":[97],"AVSE":[98,114],"not":[100],"only":[101],"outperforms":[102],"its":[103],"audio-only":[104],"counterpart":[105],"but":[106],"also":[107],"generalizes":[108],"better":[109,123],"than":[110],"recent":[112],"supervised-generative":[113],"method.":[115,135],"Additionally,":[116],"inference":[119,126],"algorithm":[120],"offers":[121],"balance":[124],"between":[125],"speed":[127],"performance":[129],"compared":[130],"previous":[133],"Code":[136],"demo":[138],"available":[139],"at:":[140],"https://jeaneudesayilo.github.io/fast_UdiffSE":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}