{"id":"https://openalex.org/W4214921663","doi":"https://doi.org/10.1109/taslp.2022.3155286","title":"SkipConvGAN: Monaural Speech Dereverberation Using Generative Adversarial Networks via Complex Time-Frequency Masking","display_name":"SkipConvGAN: Monaural Speech Dereverberation Using Generative Adversarial Networks via Complex Time-Frequency Masking","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4214921663","doi":"https://doi.org/10.1109/taslp.2022.3155286"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3155286","doi":"https://doi.org/10.1109/taslp.2022.3155286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3155286","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.12623","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047630225","display_name":"Vinay Kothapally","orcid":"https://orcid.org/0000-0002-2111-3333","observed_orcids":["https://orcid.org/0000-0002-2111-3333"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinay Kothapally","raw_affiliation_strings":["Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-2111-3333","affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-1382-9929","affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":2.1897,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.8768875,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"1600","last_page":"1613"},"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":9.999999747378752e-05,"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/T11309","display_name":"Music and Audio Processing","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generative-adversarial-networks","display_name":"generative adversarial networks","score":0.8510000109672546},{"id":"https://openalex.org/keywords/single-channel-speech-enhancement","display_name":"single-channel speech enhancement","score":0.7820000052452087},{"id":"https://openalex.org/keywords/room-acoustics","display_name":"room acoustics","score":0.5960000157356262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047502040863037},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7090376019477844},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.6778968572616577},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6613835692405701},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6581757068634033},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.6419328451156616},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.630018949508667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6290425062179565},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4538622200489044},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4518057107925415},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4249556064605713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3713846206665039},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.26600950956344604},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17485466599464417},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10883182287216187},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.08244666457176208},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.07893884181976318},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2022.3155286","doi":"https://doi.org/10.1109/taslp.2022.3155286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3155286","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2211.12623","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.12623","pdf_url":"https://arxiv.org/pdf/2211.12623","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,"listed_in":[],"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":"doi:10.48550/arxiv.2211.12623","doi":"https://doi.org/10.48550/arxiv.2211.12623","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.12623","pdf_url":null,"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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.12623","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.12623","pdf_url":"https://arxiv.org/pdf/2211.12623","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G653523863","display_name":null,"funder_award_id":"1918032","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1989314204","https://openalex.org/W2013608223","https://openalex.org/W2077626438","https://openalex.org/W2097117768","https://openalex.org/W2099168648","https://openalex.org/W2110322414","https://openalex.org/W2125114513","https://openalex.org/W2130722890","https://openalex.org/W2147166770","https://openalex.org/W2157331557","https://openalex.org/W2158336491","https://openalex.org/W2164502538","https://openalex.org/W2188162373","https://openalex.org/W2194775991","https://openalex.org/W2242685705","https://openalex.org/W2291877678","https://openalex.org/W2395263859","https://openalex.org/W2434741482","https://openalex.org/W2493745289","https://openalex.org/W2511710182","https://openalex.org/W2552465644","https://openalex.org/W2593414223","https://openalex.org/W2600556233","https://openalex.org/W2605135824","https://openalex.org/W2618946976","https://openalex.org/W2626778328","https://openalex.org/W2746457594","https://openalex.org/W2768416973","https://openalex.org/W2768546798","https://openalex.org/W2780046032","https://openalex.org/W2785678896","https://openalex.org/W2804078698","https://openalex.org/W2807888536","https://openalex.org/W2810843531","https://openalex.org/W2886938596","https://openalex.org/W2899423466","https://openalex.org/W2928133111","https://openalex.org/W2937484199","https://openalex.org/W2938901746","https://openalex.org/W2943895317","https://openalex.org/W2962785568","https://openalex.org/W2963197115","https://openalex.org/W2963446712","https://openalex.org/W2991361823","https://openalex.org/W3002137088","https://openalex.org/W3026111682","https://openalex.org/W3032514799","https://openalex.org/W3042853995","https://openalex.org/W3088490496","https://openalex.org/W3096159803","https://openalex.org/W3096408984","https://openalex.org/W3096831136","https://openalex.org/W3134695619","https://openalex.org/W4234774358","https://openalex.org/W4245919820","https://openalex.org/W4246193833","https://openalex.org/W4308909683","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W7162831328","https://openalex.org/W2886938596","https://openalex.org/W4391827462","https://openalex.org/W4391216223","https://openalex.org/W3042853995","https://openalex.org/W2795050058","https://openalex.org/W7037072360","https://openalex.org/W2609317876","https://openalex.org/W3083434315","https://openalex.org/W4412445769"],"abstract_inverted_index":{"With":[0],"the":[1,7,14,25,62,67,91,102,108,141,147,151,157,172,176],"advancements":[2],"in":[3,13,34,49,145],"deep":[4,57,193],"learning":[5],"approaches,":[6],"performance":[8,158],"of":[9,16,42,56,110,122,159,168,175],"speech":[10,170],"enhancing":[11],"systems":[12,59],"presence":[15],"background":[17],"noise":[18],"have":[19,82],"shown":[20],"significant":[21],"improvements.":[22],"However,":[23],"improving":[24],"system\u2019s":[26,129],"robustness":[27],"against":[28],"reverberation":[29,37],"is":[30],"still":[31],"a":[32,75,184],"work":[33,125],"progress,":[35],"as":[36],"tends":[38],"to":[39,46,133,149],"cause":[40],"loss":[41],"formant":[43,93,103,153],"structure":[44,94,104],"due":[45],"smearing":[47],"effects":[48],"time":[50],"and":[51,65,165],"frequency.":[52],"A":[53],"wide":[54],"range":[55],"learning-based":[58,194],"either":[60],"enhance":[61,71],"magnitude":[63],"response":[64],"reuse":[66],"distorted":[68],"phase":[69],"or":[70],"complex":[72,76,137],"spectrogram":[73],"using":[74],"time-frequency":[77,138],"mask.":[78],"Though":[79],"these":[80],"approaches":[81],"demonstrated":[83],"satisfactory":[84],"performance,":[85],"they":[86],"do":[87],"not":[88],"directly":[89],"address":[90],"lost":[92,152],"caused":[95],"by":[96],"reverberation.":[97],"We":[98,155],"believe":[99],"that":[100],"retrieving":[101],"can":[105],"help":[106],"improve":[107],"efficiency":[109],"existing":[111],"systems.":[112],"In":[113],"this":[114],"study,":[115],"we":[116],"propose":[117],"SkipConvGAN":[118],"-":[119],"an":[120,135],"extension":[121],"our":[123,160],"prior":[124],"SkipConvNet.":[126],"The":[127,180],"proposed":[128,161,181],"generator":[130,148],"network":[131,143],"tries":[132],"estimate":[134],"efficient":[136],"mask,":[139],"while":[140],"discriminator":[142],"aids":[144],"driving":[146],"restore":[150],"structure.":[154],"evaluate":[156],"system":[162,182],"on":[163],"simulated":[164],"real":[166],"recordings":[167],"reverberant":[169],"from":[171],"single-channel":[173],"task":[174],"REVERB":[177],"challenge":[178],"corpus.":[179],"shows":[183],"consistent":[185],"improvement":[186],"across":[187],"multiple":[188],"room":[189],"configurations":[190],"over":[191],"other":[192],"generative":[195],"adversarial":[196],"frameworks.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2022-03-05T00:00:00"}
