{"id":"https://openalex.org/W4392903364","doi":"https://doi.org/10.1109/icassp48485.2024.10447736","title":"Unsupervised Speech Enhancement with Diffusion-Based Generative Models","display_name":"Unsupervised Speech Enhancement with Diffusion-Based Generative Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903364","doi":"https://doi.org/10.1109/icassp48485.2024.10447736"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447736","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/A5092912264","display_name":"Bern\u00e9 Nortier","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":"Bern\u00e9 Nortier","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/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":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12481","last_page":"12485"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9929999709129333,"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"}},{"id":"https://openalex.org/T13289","display_name":"Infant Health and Development","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.768022358417511},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7450000047683716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.565654456615448},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5141754150390625},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.509515106678009},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.46006524562835693},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.45949485898017883},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4109441936016083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3998606204986572},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35476526618003845},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2712298333644867},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2236291468143463}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.768022358417511},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7450000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.565654456615448},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5141754150390625},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.509515106678009},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46006524562835693},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45949485898017883},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4109441936016083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3998606204986572},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35476526618003845},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2712298333644867},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2236291468143463},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447736","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"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W891534129","https://openalex.org/W1552314771","https://openalex.org/W1959608418","https://openalex.org/W1991111872","https://openalex.org/W2039844283","https://openalex.org/W2101045344","https://openalex.org/W2129069237","https://openalex.org/W2516001803","https://openalex.org/W2747876639","https://openalex.org/W2766672686","https://openalex.org/W2959300817","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W3005621653","https://openalex.org/W3015791137","https://openalex.org/W3097756030","https://openalex.org/W3174264304","https://openalex.org/W4221144097","https://openalex.org/W4225302959","https://openalex.org/W4281820413","https://openalex.org/W4297841790","https://openalex.org/W4309952798","https://openalex.org/W4375869120","https://openalex.org/W4380434618","https://openalex.org/W6640963894","https://openalex.org/W6679045638","https://openalex.org/W6765775151","https://openalex.org/W6786375611","https://openalex.org/W6847029043"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W1630865680","https://openalex.org/W4214692512","https://openalex.org/W4321636575","https://openalex.org/W1986418932","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W4311117049","https://openalex.org/W2770818364","https://openalex.org/W4223452531"],"abstract_inverted_index":{"Recently,":[0],"conditional":[1],"score-based":[2,72],"diffusion":[3,50,73],"models":[4,141],"have":[5],"gained":[6],"significant":[7],"attention":[8],"in":[9,41,53,64,173],"the":[10,46,65,97,128,135],"field":[11],"of":[12,49,130],"supervised":[13,162],"speech":[14,59,81,93,100,107,119,144,175],"enhancement,":[15,145],"yielding":[16],"state-of-the-art":[17,160],"performance.":[18],"However,":[19],"these":[20],"methods":[21],"may":[22],"face":[23],"challenges":[24],"when":[25],"generalising":[26],"to":[27,77,150],"unseen":[28],"conditions.":[29],"To":[30,127],"address":[31],"this":[32,133],"issue,":[33],"we":[34,86],"introduce":[35],"an":[36,42,122],"alternative":[37],"approach":[38,157],"that":[39],"operates":[40],"unsupervised":[43,143,156,174],"manner,":[44],"leveraging":[45],"generative":[47,140],"power":[48],"models.":[51],"Specifically,":[52],"a":[54,57,88,103,151,159,167],"training":[55],"phase,":[56],"clean":[58,80,99,118],"prior":[60,101],"distribution":[61],"is":[62,134],"learnt":[63,98,115],"short-time":[66],"Fourier":[67],"transform":[68],"(STFT)":[69],"domain":[70],"using":[71],"models,":[74],"allowing":[75],"it":[76],"unconditionally":[78],"generate":[79],"from":[82],"Gaussian":[83],"noise.":[84],"Then,":[85],"develop":[87],"posterior":[89],"sampling":[90],"methodology":[91],"for":[92,106,142,170],"enhancement":[94],"by":[95],"combining":[96],"with":[102,117],"noise":[104,111],"model":[105],"signal":[108],"inference.":[109],"The":[110],"parameters":[112],"are":[113],"simultaneously":[114],"along":[116],"estimation":[120],"through":[121],"iterative":[123],"expectation-maximisation":[124],"(EM)":[125],"approach.":[126],"best":[129],"our":[131],"knowledge,":[132],"first":[136],"work":[137],"exploring":[138],"diffusion-based":[139,161],"demonstrating":[146],"promising":[147],"results":[148],"compared":[149],"recent":[152],"variational":[153],"auto-encoder":[154],"(VAE)-based":[155],"and":[158],"method.":[163],"It":[164],"thus":[165],"opens":[166],"new":[168],"direction":[169],"future":[171],"research":[172],"enhancement.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}