{"id":"https://openalex.org/W2998832642","doi":"https://doi.org/10.1109/lsp.2020.3025020","title":"Improving GANs for Speech Enhancement","display_name":"Improving GANs for Speech Enhancement","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W2998832642","doi":"https://doi.org/10.1109/lsp.2020.3025020","mag":"2998832642"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2020.3025020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2020.3025020","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/handle/123456789/660522","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Huy Phan","orcid":"https://orcid.org/0000-0003-4096-785X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":["Queen Mary University of London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0003-4096-785X","affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ian V. McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ian V. McLoughlin","raw_affiliation_strings":["Singapore Institute of Technology, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7111-2008","affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology, Singapore","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lam Pham","orcid":"https://orcid.org/0000-0001-8155-7553"},"institutions":[{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lam Pham","raw_affiliation_strings":["University of Kent, Canterbury, U.K"],"raw_orcid":"https://orcid.org/0000-0001-8155-7553","affiliations":[{"raw_affiliation_string":"University of Kent, Canterbury, U.K","institution_ids":["https://openalex.org/I20581793"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Oliver Y. Chen","orcid":"https://orcid.org/0000-0002-5696-3127"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Y. Chen","raw_affiliation_strings":["University of Oxford, Oxford, OX1, U.K"],"raw_orcid":"https://orcid.org/0000-0002-5696-3127","affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, OX1, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Philipp Koch","orcid":null},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Koch","raw_affiliation_strings":["University of L\u00fcbeck, L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of L\u00fcbeck, L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Maarten De Vos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maarten De Vos","raw_affiliation_strings":["KU Leven, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KU Leven, Leuven, Belgium","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Alfred Mertins","orcid":"https://orcid.org/0000-0001-5718-577X"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alfred Mertins","raw_affiliation_strings":["University of L\u00fcbeck, L\u00fcbeck, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5718-577X","affiliations":[{"raw_affiliation_string":"University of L\u00fcbeck, L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.4413,"has_fulltext":false,"cited_by_count":131,"citation_normalized_percentile":{"value":0.99111205,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"27","issue":null,"first_page":"1700","last_page":"1704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8658000230789185,"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":0.8658000230789185,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.07859999686479568,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11448","display_name":"Face recognition and analysis","score":0.011599999852478504,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speech-enhancement","display_name":"Speech enhancement","score":0.9057999849319458},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.7023000121116638},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42399999499320984},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.4018999934196472},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.39969998598098755},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.39959999918937683},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39469999074935913},{"id":"https://openalex.org/keywords/performance-enhancement","display_name":"Performance enhancement","score":0.38769999146461487}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.9057999849319458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900999784469604},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.7023000121116638},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4991999864578247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42899999022483826},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42399999499320984},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.4018999934196472},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C2986800882","wikidata":"https://www.wikidata.org/wiki/Q7168187","display_name":"Performance enhancement","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3253999948501587},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2921999990940094},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C207912722","wikidata":"https://www.wikidata.org/wiki/Q1259123","display_name":"Signal generator","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/lsp.2020.3025020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2020.3025020","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/660522","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/660522","pdf_url":null,"source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Ieee Signal Processing Letters, vol. 27, (1700-1704)","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:arXiv.org:2001.05532","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.05532","pdf_url":"https://arxiv.org/pdf/2001.05532","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:figshare.com:article/19993667","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Improving_GANs_for_Speech_Enhancement/19993667","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":null,"raw_type":"Text"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/67344","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/67344","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/660522","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/660522","pdf_url":null,"source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Ieee Signal Processing Letters, vol. 27, (1700-1704)","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1677182931","https://openalex.org/W1897240248","https://openalex.org/W1983108229","https://openalex.org/W1995536493","https://openalex.org/W2042407743","https://openalex.org/W2044893557","https://openalex.org/W2051428568","https://openalex.org/W2094721231","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2141998673","https://openalex.org/W2593414223","https://openalex.org/W2603567530","https://openalex.org/W2787069756","https://openalex.org/W2791210709","https://openalex.org/W2791621240","https://openalex.org/W2883583470","https://openalex.org/W2924149053","https://openalex.org/W2962946126","https://openalex.org/W2963073614","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963420272","https://openalex.org/W2963453742","https://openalex.org/W2972381775","https://openalex.org/W2972785266","https://openalex.org/W4253928870","https://openalex.org/W6631190155","https://openalex.org/W6685352114","https://openalex.org/W6694517276","https://openalex.org/W6718379498"],"related_works":[],"abstract_inverted_index":{"Generative":[0],"adversarial":[1],"networks":[2],"(GAN)":[3],"have":[4],"recently":[5],"been":[6],"shown":[7],"to":[8,30,40,47,86,114,152],"be":[9],"efficient":[10],"for":[11],"speech":[12,20],"enhancement.":[13],"However,":[14],"most,":[15],"if":[16],"not":[17],"all,":[18],"existing":[19],"enhancement":[21,33,50,97,118,140],"GANs":[22],"(SEGAN)":[23],"make":[24],"use":[25,41],"of":[26,123,129],"a":[27,60,88,102],"single":[28],"generator":[29],"perform":[31,48],"one-stage":[32,144],"mapping.":[34],"In":[35],"this":[36],"work,":[37],"we":[38,64],"propose":[39],"multiple":[42],"generators":[43,70,85,113,150],"that":[44,91,136],"are":[45,79],"chained":[46],"multi-stage":[49,139],"mapping,":[51],"which":[52],"gradually":[53],"refines":[54],"the":[55,69,76,84,107,109,112,124,127,137,143,148,157],"noisy":[56],"input":[57],"signals":[58],"in":[59,101],"stage-wise":[61],"fashion.":[62],"Furthermore,":[63],"study":[65],"two":[66],"scenarios:":[67],"(1)":[68],"share":[71],"their":[72],"parameters":[73,78],"and":[74,99],"(2)":[75],"generators'":[77],"independent.":[80],"The":[81,160],"former":[82],"constrains":[83],"learn":[87,116],"common":[89],"mapping":[90],"is":[92,163],"iteratively":[93],"applied":[94],"at":[95,120,126,165],"all":[96],"stages":[98,122],"results":[100,155],"small":[103],"model":[104,132],"footprint.":[105],"On":[106],"contrary,":[108],"latter":[110],"allows":[111],"flexibly":[115],"different":[117,121],"mappings":[119],"network":[125],"cost":[128],"an":[130],"increased":[131],"size.":[133],"We":[134],"demonstrate":[135],"proposed":[138],"approach":[141],"outperforms":[142],"SEGAN":[145],"baseline,":[146],"where":[147],"independent":[149],"lead":[151],"more":[153],"favorable":[154],"than":[156],"tied":[158],"generators.":[159],"source":[161],"code":[162],"available":[164],"http://github.com/pquochuy/idsegan.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":33},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2020-01-23T00:00:00"}