{"id":"https://openalex.org/W2929514213","doi":"https://doi.org/10.21437/interspeech.2019-2688","title":"Towards Generalized Speech Enhancement with Generative Adversarial Networks","display_name":"Towards Generalized Speech Enhancement with Generative Adversarial Networks","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2929514213","doi":"https://doi.org/10.21437/interspeech.2019-2688","mag":"2929514213"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2688","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.03418","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101557983","display_name":"Santiago Pascual","orcid":"https://orcid.org/0000-0002-8365-7387"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Santiago Pascual","raw_affiliation_strings":["[Polytechnic University of Catalonia]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Polytechnic University of Catalonia]","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103092198","display_name":"Joan Serr\u00e0","orcid":"https://orcid.org/0000-0003-1303-6558"},"institutions":[{"id":"https://openalex.org/I134820265","display_name":"Consejo Superior de Investigaciones Cient\u00edficas","ror":"https://ror.org/02gfc7t72","country_code":"ES","type":"government","lineage":["https://openalex.org/I134820265"]},{"id":"https://openalex.org/I4210117526","display_name":"Unidades Centrales Cient\u00edfico-T\u00e9cnicas","ror":"https://ror.org/01wdt4y78","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2801357902","https://openalex.org/I4210117526","https://openalex.org/I4387152914"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Joan Serr\u00e0","raw_affiliation_strings":["Consejo Superior de Investigaciones Cient\u00edficas, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Consejo Superior de Investigaciones Cient\u00edficas, Madrid, Spain","institution_ids":["https://openalex.org/I134820265","https://openalex.org/I4210117526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000405202","display_name":"Antonio Bonafonte","orcid":"https://orcid.org/0000-0002-6240-9915"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Bonafonte","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1791","last_page":"1795"},"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":0.9954000115394592,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8138383626937866},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.7437309622764587},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7287334203720093},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7137097120285034},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.697452187538147},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5630213618278503},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5507118701934814},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.43790096044540405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35822567343711853},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1983918845653534},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1798209846019745},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1103992760181427}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8138383626937866},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.7437309622764587},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7287334203720093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7137097120285034},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.697452187538147},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5630213618278503},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5507118701934814},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.43790096044540405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35822567343711853},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1983918845653534},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1798209846019745},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1103992760181427},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","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":4,"locations":[{"id":"doi:10.21437/interspeech.2019-2688","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.03418","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03418","pdf_url":"https://arxiv.org/pdf/1904.03418","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"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":"mag:2929514213","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.03418v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1904.03418","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.03418","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.03418","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03418","pdf_url":"https://arxiv.org/pdf/1904.03418","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"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"},"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2929514213.pdf","grobid_xml":"https://content.openalex.org/works/W2929514213.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1677182931","https://openalex.org/W1897240248","https://openalex.org/W2042407743","https://openalex.org/W2044893557","https://openalex.org/W2099471712","https://openalex.org/W2107860279","https://openalex.org/W2173520492","https://openalex.org/W2405774341","https://openalex.org/W2527729766","https://openalex.org/W2548275288","https://openalex.org/W2562274522","https://openalex.org/W2593414223","https://openalex.org/W2594927458","https://openalex.org/W2609317876","https://openalex.org/W2786254735","https://openalex.org/W2787069756","https://openalex.org/W2804078698","https://openalex.org/W2883583470","https://openalex.org/W2893749619","https://openalex.org/W2962795274","https://openalex.org/W2962997440","https://openalex.org/W2963041308","https://openalex.org/W2963073614","https://openalex.org/W2963103134","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963453742","https://openalex.org/W2963782041","https://openalex.org/W2963836885","https://openalex.org/W2963975282","https://openalex.org/W2963981733"],"related_works":["https://openalex.org/W2972785266","https://openalex.org/W3005262054","https://openalex.org/W2892356933","https://openalex.org/W2971758476","https://openalex.org/W3015411705","https://openalex.org/W3088108644","https://openalex.org/W3031135612","https://openalex.org/W3134320247","https://openalex.org/W3156248872","https://openalex.org/W2948661109","https://openalex.org/W3015910825","https://openalex.org/W3004282423","https://openalex.org/W3158448163","https://openalex.org/W2963321191","https://openalex.org/W3007217021","https://openalex.org/W3098606562","https://openalex.org/W3180992661","https://openalex.org/W3164736513","https://openalex.org/W2610957433","https://openalex.org/W3131305672"],"abstract_inverted_index":{"The":[0],"speech":[1,74,97,159],"enhancement":[2,75,98],"task":[3],"usually":[4],"consists":[5],"of":[6,60,104,107,115,135],"removing":[7],"additive":[8],"noise":[9],"or":[10,36,54],"reverberation":[11],"that":[12,121,153,161],"partially":[13],"mask":[14],"spoken":[15],"utterances,":[16],"affecting":[17],"their":[18],"intelligibility.":[19],"However,":[20],"little":[21],"attention":[22],"is":[23],"drawn":[24],"to":[25,71,100],"other,":[26],"perhaps":[27],"more":[28],"aggressive":[29,108],"signal":[30,62],"distortions":[31,40],"like":[32],"clipping,":[33],"chunk":[34],"elimination,":[35],"frequency-band":[37],"removal.":[38],"Such":[39],"can":[41,80],"have":[42],"a":[43,84,94,123,136,143],"large":[44],"impact":[45],"not":[46],"only":[47],"on":[48,52],"intelligibility,":[49],"but":[50],"also":[51,132],"naturalness":[53],"even":[55],"speaker":[56,166],"identity,":[57],"and":[58,77,149,168],"require":[59],"careful":[61],"reconstruction.":[63],"In":[64,90],"this":[65,72],"work,":[66],"we":[67,92,111,131],"give":[68],"full":[69],"consideration":[70],"generalized":[73],"task,":[76],"show":[78,152],"it":[79],"be":[81],"tackled":[82],"with":[83,102],"time-domain":[85],"generative":[86],"adversarial":[87,117,138],"network":[88],"(GAN).":[89],"particular,":[91],"extend":[93],"previous":[95],"GAN-based":[96],"system":[99],"deal":[101],"mixtures":[103],"four":[105],"types":[106],"distortions.":[109],"Firstly,":[110],"propose":[112],"the":[113,128,164],"addition":[114],"an":[116],"acoustic":[118],"regression":[119],"loss":[120],"promotes":[122],"richer":[124],"feature":[125],"extraction":[126],"at":[127],"discriminator.":[129],"Secondly,":[130],"make":[133],"use":[134],"two-step":[137],"training":[139],"schedule,":[140],"acting":[141],"as":[142],"warm":[144],"up-and-fine-tune":[145],"sequence.":[146],"Both":[147],"objective":[148],"subjective":[150],"evaluations":[151],"these":[154],"two":[155],"additions":[156],"bring":[157],"improved":[158],"reconstructions":[160],"better":[162],"match":[163],"original":[165],"identity":[167],"naturalness.":[169]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
