{"id":"https://openalex.org/W4311841164","doi":"https://doi.org/10.1109/icassp49357.2023.10094849","title":"Audio-Visual Speech Enhancement with a Deep Kalman Filter Generative Model","display_name":"Audio-Visual Speech Enhancement with a Deep Kalman Filter Generative Model","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4311841164","doi":"https://doi.org/10.1109/icassp49357.2023.10094849"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044728356","display_name":"Ali Golmakani","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"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ali Golmakani","raw_affiliation_strings":["Université de Lorraine, CNRS, Inria, LORIA,Nancy,France,F-54000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS, Inria, LORIA,Nancy,France,F-54000","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838","https://openalex.org/I90183372"]}]},{"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/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"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["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,F-54000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS, Inria, LORIA,Nancy,France,F-54000","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838","https://openalex.org/I90183372"]}]},{"author_position":"last","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"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["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,F-54000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS, Inria, LORIA,Nancy,France,F-54000","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838","https://openalex.org/I90183372"]}]}],"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":6,"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":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":0.9983999729156494,"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":0.9929999709129333,"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":0.7925782203674316},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7180348038673401},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6083277463912964},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6077211499214172},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5404478311538696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5302913784980774},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5129620432853699},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4606035351753235},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.41864654421806335},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3698372542858124},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3480478823184967},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3264460861682892},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.28581133484840393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925782203674316},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7180348038673401},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6083277463912964},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6077211499214172},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5404478311538696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5302913784980774},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5129620432853699},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4606035351753235},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.41864654421806335},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3698372542858124},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3480478823184967},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3264460861682892},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28581133484840393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1959608418","https://openalex.org/W2029199293","https://openalex.org/W2141998673","https://openalex.org/W2747876639","https://openalex.org/W2766672686","https://openalex.org/W2883322837","https://openalex.org/W2963082324","https://openalex.org/W2963375116","https://openalex.org/W2964058413","https://openalex.org/W2964171275","https://openalex.org/W2964232608","https://openalex.org/W2965390715","https://openalex.org/W3005621653","https://openalex.org/W3015791137","https://openalex.org/W3016011581","https://openalex.org/W3033703941","https://openalex.org/W3136499730","https://openalex.org/W3137758952","https://openalex.org/W3160658686","https://openalex.org/W3174264304","https://openalex.org/W3217536461","https://openalex.org/W4225725085","https://openalex.org/W4289665794","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6810565155"],"related_works":["https://openalex.org/W2988134182","https://openalex.org/W2470043383","https://openalex.org/W2953501176","https://openalex.org/W2965095304","https://openalex.org/W3034474024","https://openalex.org/W2770818364","https://openalex.org/W4317242571","https://openalex.org/W2944085132","https://openalex.org/W2616125534","https://openalex.org/W2770703741"],"abstract_inverted_index":{"Deep":[0],"latent":[1,111],"variable":[2],"generative":[3,62,100,143],"models":[4,63,144],"based":[5],"on":[6],"variational":[7],"autoencoder":[8],"(VAE)":[9],"have":[10],"shown":[11],"promising":[12],"performance":[13],"for":[14,30,65,109,145],"audio-visual":[15,27,95,116,168],"speech":[16,32,46,76,127,146],"enhancement":[17],"(AVSE).":[18],"The":[19,148],"underlying":[20],"idea":[21],"is":[22],"to":[23,43,125,138],"learn":[24],"a":[25,39,45,49,104,134],"VAE-based":[26,169],"prior":[28],"distribution":[29],"clean":[31],"data,":[33,77],"and":[34,53,113,163,167],"then":[35],"combine":[36],"it":[37],"with":[38,158],"statistical":[40],"noise":[41],"model":[42,101,108,156],"recover":[44],"signal":[47],"from":[48,81],"noisy":[50],"audio":[51],"recording":[52],"video":[54],"(lip":[55],"images)":[56],"of":[57,75,86,136,142,153],"the":[58,72,84,110,151,154,164],"target":[59],"speaker.":[60],"Existing":[61],"developed":[64],"AVSE":[66],"do":[67],"not":[68],"take":[69],"into":[70],"account":[71],"sequential":[73],"nature":[74],"which":[78,102],"prevents":[79],"them":[80],"fully":[82],"incorporating":[83],"power":[85],"visual":[87],"data.":[88,117],"In":[89],"this":[90],"paper,":[91],"we":[92,119],"present":[93],"an":[94,121],"deep":[96],"Kalman":[97],"filter":[98],"(AV-DKF)":[99],"assumes":[103],"first-order":[105],"Markov":[106],"chain":[107],"variables":[112],"effectively":[114],"fuses":[115],"Moreover,":[118],"develop":[120],"efficient":[122],"inference":[123],"methodology":[124],"estimate":[126],"signals":[128],"at":[129],"test":[130],"time.":[131],"We":[132],"conduct":[133],"set":[135],"experiments":[137],"compare":[139],"different":[140],"variants":[141],"enhancement.":[147],"results":[149],"demonstrate":[150],"superiority":[152],"AV-DKF":[155],"compared":[157],"both":[159],"its":[160],"audio-only":[161,166],"version":[162],"non-sequential":[165],"models.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}