{"id":"https://openalex.org/W4392903707","doi":"https://doi.org/10.1109/icassp48485.2024.10447837","title":"Posterior Sampling Algorithms for Unsupervised Speech Enhancement with Recurrent Variational Autoencoder","display_name":"Posterior Sampling Algorithms for Unsupervised Speech Enhancement with Recurrent Variational Autoencoder","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903707","doi":"https://doi.org/10.1109/icassp48485.2024.10447837"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/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"]},{"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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12466","last_page":"12470"},"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":0.9976999759674072,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7298514246940613},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6634423732757568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6375633478164673},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5739092826843262},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5711885690689087},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5140987038612366},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4528416693210602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44329914450645447},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4171915054321289},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.41459235548973083},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3237497806549072},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.28779536485671997},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2591215968132019},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22954177856445312},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1208905279636383}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7298514246940613},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6634423732757568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6375633478164673},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5739092826843262},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5711885690689087},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5140987038612366},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4528416693210602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44329914450645447},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4171915054321289},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.41459235548973083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3237497806549072},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28779536485671997},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2591215968132019},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22954177856445312},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1208905279636383},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"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"},{"id":"https://openalex.org/G3780308692","display_name":null,"funder_award_id":"ANR-22-CE23-0026-01","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"},{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W891534129","https://openalex.org/W1552314771","https://openalex.org/W1556278552","https://openalex.org/W2044893557","https://openalex.org/W2101045344","https://openalex.org/W2289394825","https://openalex.org/W2516001803","https://openalex.org/W2560674852","https://openalex.org/W2747876639","https://openalex.org/W2766672686","https://openalex.org/W2918296821","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W3005621653","https://openalex.org/W3097756030","https://openalex.org/W3130335839","https://openalex.org/W3174264304","https://openalex.org/W4212863985","https://openalex.org/W4221144097","https://openalex.org/W4292403327","https://openalex.org/W4311841227","https://openalex.org/W4375869120","https://openalex.org/W4380434618","https://openalex.org/W6640963894","https://openalex.org/W6684809622","https://openalex.org/W6786375611"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2145836866","https://openalex.org/W2263596235"],"abstract_inverted_index":{"In":[0],"this":[1,51],"paper,":[2],"we":[3,53,85],"address":[4],"the":[5,23,27,67,77,82,87,99,141],"unsupervised":[6],"speech":[7,69,108],"enhancement":[8,70,109],"problem":[9],"based":[10,58,111],"on":[11,39,59,112],"recurrent":[12],"variational":[13,30,41,90],"autoencoder":[14],"(RVAE).":[15],"This":[16],"approach":[17,110],"offers":[18],"promising":[19],"generalization":[20,148],"performance":[21,149],"over":[22],"supervised":[24,107,142],"counterpart.":[25],"Nevertheless,":[26],"involved":[28],"iterative":[29],"expectation-maximization":[31],"(VEM)":[32],"process":[33],"at":[34],"test":[35,152],"time,":[36],"which":[37],"relies":[38],"a":[40,94,105],"inference":[42],"method,":[43],"results":[44,116],"in":[45,127,134,150],"high":[46],"computational":[47,130],"complexity.":[48],"To":[49],"tackle":[50],"issue,":[52],"present":[54],"efficient":[55],"sampling":[56,75],"techniques":[57],"Langevin":[60],"dynamics":[61],"and":[62,104],"Metropolis-Hasting":[63],"algorithms,":[64],"adapted":[65],"to":[66,140],"EM-based":[68],"with":[71,102],"RVAE.":[72],"By":[73],"directly":[74],"from":[76],"intractable":[78],"posterior":[79],"distribution":[80],"within":[81],"EM":[83],"process,":[84],"circumvent":[86],"intricacies":[88],"of":[89,96,129],"inference.":[91],"We":[92],"conduct":[93],"series":[95],"experiments,":[97],"comparing":[98],"proposed":[100],"methods":[101,145],"VEM":[103],"state-of-the-art":[106],"diffusion":[113],"models.":[114],"The":[115],"reveal":[117],"that":[118],"our":[119,144],"sampling-based":[120],"algorithms":[121],"significantly":[122],"outperform":[123],"VEM,":[124],"not":[125],"only":[126],"terms":[128],"efficiency":[131],"but":[132],"also":[133],"overall":[135],"performance.":[136],"Furthermore,":[137],"when":[138],"compared":[139],"baseline,":[143],"showcase":[146],"robust":[147],"mismatched":[151],"conditions.":[153]},"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"}