{"id":"https://openalex.org/W4392931780","doi":"https://doi.org/10.1109/icassp48485.2024.10446805","title":"Diffusion-Based Speech Enhancement with a Weighted Generative-Supervised Learning Loss","display_name":"Diffusion-Based Speech Enhancement with a Weighted Generative-Supervised Learning Loss","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931780","doi":"https://doi.org/10.1109/icassp48485.2024.10446805"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446805","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/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"]},{"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":"Jean-Eudes Ayilo","raw_affiliation_strings":["Universit&#x00E9; de Lorraine,CNRS, Inria, LORIA,Nancy,France,F-54000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; 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":["Universit&#x00E9; de Lorraine,CNRS, Inria, LORIA,Nancy,France,F-54000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; 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":["Universit&#x00E9; de Lorraine,CNRS, Inria, LORIA,Nancy,France,F-54000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; 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":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12506","last_page":"12510"},"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":0.9980000257492065,"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":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.6974352598190308},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.629917562007904},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6093723177909851},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5812037587165833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5308032631874084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5288413763046265},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5275242924690247},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5112729072570801},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48948538303375244},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.42519310116767883},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.41486990451812744},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.41484907269477844},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37672725319862366},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3478321433067322},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.24486416578292847},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1898401975631714},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17932313680648804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6974352598190308},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.629917562007904},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6093723177909851},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5812037587165833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5308032631874084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5288413763046265},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5275242924690247},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5112729072570801},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48948538303375244},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.42519310116767883},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.41486990451812744},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.41484907269477844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37672725319862366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3478321433067322},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24486416578292847},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1898401975631714},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17932313680648804},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446805","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":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"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":24,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W891534129","https://openalex.org/W1552314771","https://openalex.org/W1991111872","https://openalex.org/W2013035813","https://openalex.org/W2015810892","https://openalex.org/W2044893557","https://openalex.org/W2516001803","https://openalex.org/W2747876639","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W3005621653","https://openalex.org/W4221144097","https://openalex.org/W4225302959","https://openalex.org/W4232282348","https://openalex.org/W4375869120","https://openalex.org/W4380434618","https://openalex.org/W4382202691","https://openalex.org/W4402111962","https://openalex.org/W6783182287","https://openalex.org/W6786375611","https://openalex.org/W6851069163","https://openalex.org/W6855309294","https://openalex.org/W6890361730"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W1494268238","https://openalex.org/W154868527","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W4255576661","https://openalex.org/W4386076228","https://openalex.org/W4310825149","https://openalex.org/W2798269247"],"abstract_inverted_index":{"Diffusion-based":[0],"generative":[1],"models":[2,19],"have":[3],"recently":[4],"gained":[5],"attention":[6],"in":[7,63],"speech":[8,22,96],"enhancement":[9],"(SE),":[10],"providing":[11],"an":[12,57,84],"alternative":[13],"to":[14,39],"conventional":[15],"supervised":[16,48],"methods.":[17],"These":[18],"transform":[20],"clean":[21,95],"training":[23,81],"samples":[24],"into":[25],"Gaussian":[26],"noise,":[27],"usually":[28],"centered":[29],"on":[30,44,56],"noisy":[31,45,69],"speech,":[32],"and":[33,97],"subsequently":[34],"learn":[35],"a":[36],"parameterized":[37],"model":[38],"reverse":[40],"this":[41,73],"process,":[42],"conditionally":[43],"speech.":[46,70],"Unlike":[47],"methods,":[49],"generative-based":[50],"SE":[51],"approaches":[52],"often":[53],"rely":[54],"solely":[55],"unsupervised":[58],"loss,":[59,89],"which":[60],"may":[61],"result":[62],"less":[64],"efficient":[65],"incorporation":[66],"of":[67,109],"conditioned":[68],"To":[71],"address":[72],"issue,":[74],"we":[75],"propose":[76],"augmenting":[77],"the":[78,91,107],"original":[79],"diffusion":[80,102],"objective":[82],"with":[83],"\u2113":[85],"<inf":[86],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[87],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</inf>":[88],"measuring":[90],"discrepancy":[92],"between":[93],"ground-truth":[94],"its":[98],"estimation":[99],"at":[100],"each":[101],"time-step.":[103],"Experimental":[104],"results":[105],"demonstrate":[106],"effectiveness":[108],"our":[110],"proposed":[111],"methodology.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}