{"id":"https://openalex.org/W2892356933","doi":"https://doi.org/10.1109/icassp.2018.8462614","title":"On Adversarial Training and Loss Functions for Speech Enhancement","display_name":"On Adversarial Training and Loss Functions for Speech Enhancement","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2892356933","doi":"https://doi.org/10.1109/icassp.2018.8462614","mag":"2892356933"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5050492887","display_name":"Ashutosh Pandey","orcid":"https://orcid.org/0000-0002-3352-7453"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Pandey","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deliang Wang","raw_affiliation_strings":["Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5414","last_page":"5418"},"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/T11309","display_name":"Music and Audio Processing","score":0.9962999820709229,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.7677088975906372},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6466360688209534},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5531455874443054},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5118898153305054},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5053454041481018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5031868815422058},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49280670285224915},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4161078631877899},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07205599546432495}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.7677088975906372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6466360688209534},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5531455874443054},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5118898153305054},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5053454041481018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5031868815422058},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49280670285224915},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4161078631877899},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07205599546432495},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1836465849","https://openalex.org/W1974387177","https://openalex.org/W2013608223","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2125389028","https://openalex.org/W2128653836","https://openalex.org/W2141998673","https://openalex.org/W2153894152","https://openalex.org/W2168379380","https://openalex.org/W2173520492","https://openalex.org/W2405774341","https://openalex.org/W2593414223","https://openalex.org/W2746457594","https://openalex.org/W2949117887","https://openalex.org/W2962866211","https://openalex.org/W2963073614","https://openalex.org/W2963341071","https://openalex.org/W2963373786","https://openalex.org/W2963420272","https://openalex.org/W2963453742","https://openalex.org/W2963684088","https://openalex.org/W4253928870","https://openalex.org/W4320013936","https://openalex.org/W6638667902","https://openalex.org/W6713658392","https://openalex.org/W6718379498"],"related_works":["https://openalex.org/W2995777218","https://openalex.org/W2953246223","https://openalex.org/W4293320219","https://openalex.org/W3110074278","https://openalex.org/W4283584549","https://openalex.org/W2618858825","https://openalex.org/W2554314924","https://openalex.org/W2998859928","https://openalex.org/W3156863413","https://openalex.org/W4381885966"],"abstract_inverted_index":{"Generative":[0],"adversarial":[1,90],"networks":[2],"(GANs)":[3],"are":[4],"becoming":[5],"increasingly":[6],"popular":[7],"for":[8,18,33,79,99,148,169],"image":[9],"processing":[10],"tasks.":[11],"Researchers":[12],"have":[13],"started":[14],"using":[15,25,66,121],"GAN":[16,27,57,78,123,137],"s":[17],"speech":[19,34,80,140,149],"enhancement,":[20,81,150],"but":[21,45],"the":[22,26,49,52,56,67,87,113,122,126,136,153,163,171],"advantage":[23],"of":[24,51,89,128,145,174],"framework":[28,124,138],"has":[29],"not":[30],"been":[31],"established":[32],"enhancement.":[35],"For":[36],"example,":[37],"a":[38,76],"recent":[39],"study":[40],"reports":[41],"encouraging":[42],"enhancement":[43,141],"results,":[44],"we":[46],"find":[47],"that":[48,135,152],"architecture":[50],"generator":[53],"used":[54,98],"in":[55,107],"gives":[58],"better":[59,161],"performance":[60,84],"when":[61],"it":[62,104],"is":[63,97,105,159],"trained":[64,106],"alone":[65],"L":[68,114,154,164],"<sub":[69,115,155,165],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[70,116,156,166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sub>":[71,117,157],"loss.":[72],"This":[73],"work":[74],"presents":[75],"new":[77],"and":[82,103,119],"obtains":[83],"improvement":[85],"with":[86,112,125],"help":[88,127],"training.":[91],"A":[92],"deep":[93],"neural":[94],"network":[95],"(DNN)":[96],"time-frequency":[100],"mask":[101],"estimation,":[102],"two":[108],"ways:":[109],"regular":[110],"training":[111,120],"loss":[118,146,158,168],"an":[129],"adversary":[130],"discriminator.":[131],"Experimental":[132],"results":[133],"suggest":[134],"improves":[139],"performance.":[142],"Further":[143],"exploration":[144],"functions,":[147],"suggests":[151],"consistently":[160],"than":[162],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sub>":[167],"improving":[170],"perceptual":[172],"quality":[173],"noisy":[175],"speech.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}