{"id":"https://openalex.org/W4408355012","doi":"https://doi.org/10.1109/icassp49660.2025.10887633","title":"CorrGAN: Simultaneous Learning of Speech Enhancement and Perceptual Quality Loss Functions","display_name":"CorrGAN: Simultaneous Learning of Speech Enhancement and Perceptual Quality Loss Functions","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355012","doi":"https://doi.org/10.1109/icassp49660.2025.10887633"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5044669713","display_name":"Vasily Zadorozhnyy","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vasily Zadorozhnyy","raw_affiliation_strings":["SRI International,Princeton,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International,Princeton,USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044581608","display_name":"Saeed Amizadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saeed Amizadeh","raw_affiliation_strings":["Microsoft Corporation,Redmond,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417961","display_name":"Qiang Ye","orcid":"https://orcid.org/0000-0002-8357-221X"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Ye","raw_affiliation_strings":["University of Kentucky,Lexington,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Kentucky,Lexington,USA","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084879161","display_name":"Kazuhito Koishida","orcid":"https://orcid.org/0000-0002-3111-5375"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kazuhito Koishida","raw_affiliation_strings":["Microsoft Corporation,Redmond,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"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":1,"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":0.9970999956130981,"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":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.7090436816215515},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6471414566040039},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6415396928787231},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5842674374580383},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5756028890609741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28372421860694885},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1648726761341095},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09006300568580627},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.046653687953948975}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7090436816215515},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6471414566040039},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6415396928787231},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5842674374580383},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5756028890609741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28372421860694885},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1648726761341095},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09006300568580627},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.046653687953948975},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/icassp49660.2025.10887633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W1897240248","https://openalex.org/W2067295501","https://openalex.org/W2094721231","https://openalex.org/W2144404214","https://openalex.org/W2603567530","https://openalex.org/W2785678896","https://openalex.org/W2889442120","https://openalex.org/W2963341071","https://openalex.org/W2972481755","https://openalex.org/W3097777922","https://openalex.org/W3158779859","https://openalex.org/W3163827866","https://openalex.org/W3197912330","https://openalex.org/W3211944253","https://openalex.org/W4221143458","https://openalex.org/W4225309689","https://openalex.org/W4232282348","https://openalex.org/W4296069347","https://openalex.org/W4312918084","https://openalex.org/W4376877074","https://openalex.org/W4385245566","https://openalex.org/W4385822340","https://openalex.org/W6675521023","https://openalex.org/W6681096077","https://openalex.org/W6717367658","https://openalex.org/W6724804524","https://openalex.org/W6744762798","https://openalex.org/W6757817989","https://openalex.org/W6762114000"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Deep-learning":[0],"models":[1],"have":[2,47],"allowed":[3],"effective":[4],"end-to-end":[5],"SE":[6,63,107],"systems":[7],"in":[8,25,42],"the":[9,36,52,70,84,88,102,106,130,138],"Speech":[10],"Enhancement":[11],"(SE)":[12],"field.":[13],"Most":[14],"of":[15,54,69,87,104,129],"these":[16,30],"methods":[17],"are":[18],"trained":[19],"using":[20],"a":[21,26],"fixed":[22],"reconstruction":[23],"loss":[24],"supervised":[27],"setting.":[28],"Often":[29],"losses":[31,128],"do":[32],"not":[33],"perfectly":[34],"represent":[35],"desired":[37],"perceptual":[38],"quality":[39],"metrics,":[40],"resulting":[41],"sub-optimal":[43],"performance.":[44],"Recently,":[45],"there":[46],"been":[48],"efforts":[49],"to":[50,82,111],"learn":[51],"behavior":[53],"those":[55],"metrics":[56],"directly":[57],"via":[58],"neural":[59],"nets":[60],"for":[61,77],"training":[62,78,94],"models.":[64],"However,":[65],"an":[66,92],"accurate":[67],"estimation":[68],"true":[71],"metric":[72,108],"function":[73],"introduces":[74],"statistical":[75,98],"complexity":[76,103],"because":[79],"it":[80],"attempts":[81],"capture":[83],"exact":[85],"value":[86],"metric.":[89],"We":[90,116],"propose":[91],"adversarial":[93],"strategy":[95],"based":[96],"on":[97,137],"correlation":[99],"that":[100],"avoids":[101],"estimating":[105],"while":[109],"learning":[110],"mimic":[112],"its":[113,123],"overall":[114],"behavior.":[115],"call":[117],"this":[118],"framework":[119],"CorrGAN":[120],"and":[121,133],"show":[122],"significant":[124],"improvement":[125],"over":[126],"standard":[127],"SOTA":[131,135],"baselines":[132],"achieve":[134],"performance":[136],"VoiceBank+DEMAND":[139],"dataset.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}