{"id":"https://openalex.org/W4392909909","doi":"https://doi.org/10.1109/icassp48485.2024.10446294","title":"A Weighted-Variance Variational Autoencoder Model for Speech Enhancement","display_name":"A Weighted-Variance Variational Autoencoder Model for Speech Enhancement","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909909","doi":"https://doi.org/10.1109/icassp48485.2024.10446294"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446294","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":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-03833827/document","any_repository_has_fulltext":true},"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/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":"middle","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":["Inria Grenoble & Univ. Grenoble Alpes,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria Grenoble & Univ. Grenoble Alpes,France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I899635006"]}]},{"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":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12451","last_page":"12455"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.993399977684021,"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":0.993399977684021,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8977922201156616},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6392921805381775},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.540371298789978},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5227099657058716},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46184319257736206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38224300742149353},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3709084987640381},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34004953503608704},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10971188545227051},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06706404685974121}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8977922201156616},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6392921805381775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.540371298789978},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5227099657058716},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46184319257736206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38224300742149353},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3709084987640381},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34004953503608704},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10971188545227051},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06706404685974121},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446294","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"},{"id":"pmh:oai:HAL:hal-03833827v2","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03833827","pdf_url":"https://inria.hal.science/hal-03833827/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":"ICASSP 2024 - International Conference on Acoustics Speech and Signal Processing, IEEE, Apr 2024, Seoul (Korea), South Korea. pp.1-5, ⟨10.1109/ICASSP48485.2024.10446294⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03833827v2","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03833827","pdf_url":"https://inria.hal.science/hal-03833827/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":"ICASSP 2024 - International Conference on Acoustics Speech and Signal Processing, IEEE, Apr 2024, Seoul (Korea), South Korea. pp.1-5, ⟨10.1109/ICASSP48485.2024.10446294⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392909909.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1504438288","https://openalex.org/W1552314771","https://openalex.org/W2029199293","https://openalex.org/W2039844283","https://openalex.org/W2141998673","https://openalex.org/W2747876639","https://openalex.org/W2766672686","https://openalex.org/W2808266363","https://openalex.org/W2883322837","https://openalex.org/W2918296821","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W2963375116","https://openalex.org/W2964058413","https://openalex.org/W2965390715","https://openalex.org/W3005621653","https://openalex.org/W3011982609","https://openalex.org/W3033703941","https://openalex.org/W3131332223","https://openalex.org/W3174264304","https://openalex.org/W4211128380","https://openalex.org/W4293363567","https://openalex.org/W6640963894"],"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/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W197907117"],"abstract_inverted_index":{"We":[0,74,98],"address":[1],"speech":[2,12,34,95,103,119],"enhancement":[3,104,120],"based":[4,106],"on":[5,80,107,115],"variational":[6],"autoencoders,":[7],"which":[8,83],"involves":[9],"learning":[10,71],"a":[11,42,45,57,76,88],"prior":[13,78],"distribution":[14,24,79],"in":[15,38,69],"the":[16,29,33,39,63,81,108,122,127,132],"time-frequency":[17],"(TF)":[18],"domain.":[19],"A":[20],"zero-mean":[21],"complex-valued":[22],"Gaussian":[23,93],"is":[25,36,72],"usually":[26],"assumed":[27],"for":[28,94],"generative":[30,60,96,110],"model,":[31,61],"where":[32,62],"information":[35],"encoded":[37],"variance":[40,59,135],"as":[41],"function":[43],"of":[44,65,92,126],"latent":[46],"variable.":[47],"In":[48],"contrast":[49],"to":[50,87,131],"this":[51],"commonly":[52],"used":[53],"approach,":[54],"we":[55],"propose":[56],"weighted":[58],"contribution":[64],"each":[66],"spectrogram":[67,116],"time-frame":[68],"parameter":[70],"weighted.":[73],"impose":[75],"Gamma":[77],"weights,":[82],"would":[84],"effectively":[85],"lead":[86],"Student\u2019s":[89],"t-distribution":[90],"instead":[91],"modeling.":[97],"develop":[99],"efficient":[100],"training":[101],"and":[102,118,124],"algorithms":[105],"proposed":[109,128],"model.":[111,136],"Our":[112],"experimental":[113],"results":[114],"auto-encoding":[117],"demonstrate":[121],"effectiveness":[123],"robustness":[125],"approach":[129],"compared":[130],"standard":[133],"unweighted":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}