{"id":"https://openalex.org/W2900298217","doi":"https://doi.org/10.1109/lsp.2018.2880285","title":"Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition","display_name":"Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition","publication_year":2018,"publication_date":"2018-11-09","ids":{"openalex":"https://openalex.org/W2900298217","doi":"https://doi.org/10.1109/lsp.2018.2880285","mag":"2900298217"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2018.2880285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2018.2880285","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://arxiv.org/pdf/1811.02182","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066858751","display_name":"Geonmin Kim","orcid":"https://orcid.org/0000-0002-9704-6843"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Geonmin Kim","raw_affiliation_strings":["Department of Electrical Engineering, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054334046","display_name":"Hwaran Lee","orcid":"https://orcid.org/0000-0002-3773-4871"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwaran Lee","raw_affiliation_strings":["Department of Electrical Engineering, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103109289","display_name":"Bo-Kyeong Kim","orcid":"https://orcid.org/0000-0002-0224-7985"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bo-Kyeong Kim","raw_affiliation_strings":["Department of Electrical Engineering, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046336702","display_name":"Sang-Hoon Oh","orcid":"https://orcid.org/0000-0002-2195-9056"},"institutions":[{"id":"https://openalex.org/I3133486578","display_name":"Mokwon University","ror":"https://ror.org/01whq8m38","country_code":"KR","type":"education","lineage":["https://openalex.org/I3133486578"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-Hoon Oh","raw_affiliation_strings":["Division of Information and Communication Convergence Engineering, Mokwon University, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Division of Information and Communication Convergence Engineering, Mokwon University, Daejeon, South Korea","institution_ids":["https://openalex.org/I3133486578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100616676","display_name":"Soo-Young Lee","orcid":"https://orcid.org/0000-0003-0776-5084"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soo-Young Lee","raw_affiliation_strings":["KAIST Institute for Artificial Intelligence, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST Institute for Artificial Intelligence, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5066858751"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":2.1571,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.88703257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"26","issue":"1","first_page":"159","last_page":"163"},"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":0.9958999752998352,"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":0.9945999979972839,"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":0.7210512757301331},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6993422508239746},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5932829976081848},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5710117220878601},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4710535705089569},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.47064322233200073},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41425538063049316},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4131908714771271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3240348696708679},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12516874074935913},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10956341028213501}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210512757301331},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6993422508239746},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5932829976081848},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5710117220878601},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4710535705089569},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.47064322233200073},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41425538063049316},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4131908714771271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3240348696708679},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12516874074935913},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10956341028213501},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2018.2880285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2018.2880285","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:arXiv.org:1811.02182","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.02182","pdf_url":"https://arxiv.org/pdf/1811.02182","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.02182","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.02182","pdf_url":"https://arxiv.org/pdf/1811.02182","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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1983108229","https://openalex.org/W2008716139","https://openalex.org/W2096779346","https://openalex.org/W2119500623","https://openalex.org/W2121973264","https://openalex.org/W2125389028","https://openalex.org/W2127141656","https://openalex.org/W2153894152","https://openalex.org/W2193413348","https://openalex.org/W2243290847","https://openalex.org/W2549108983","https://openalex.org/W2559260703","https://openalex.org/W2559809918","https://openalex.org/W2592480533","https://openalex.org/W2598581049","https://openalex.org/W2600556233","https://openalex.org/W2603646652","https://openalex.org/W2605195953","https://openalex.org/W2608338293","https://openalex.org/W2617258110","https://openalex.org/W2750545698","https://openalex.org/W2768416973","https://openalex.org/W2769456121","https://openalex.org/W2771343701","https://openalex.org/W2951939904","https://openalex.org/W2962677373","https://openalex.org/W2962775818","https://openalex.org/W2962793481","https://openalex.org/W2962816167","https://openalex.org/W2962896155","https://openalex.org/W2962947361","https://openalex.org/W2962949994","https://openalex.org/W2963103134","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2964121744","https://openalex.org/W3147539069","https://openalex.org/W4232282348","https://openalex.org/W4240805545","https://openalex.org/W4295274059","https://openalex.org/W6631190155","https://openalex.org/W6678815747","https://openalex.org/W6687566353","https://openalex.org/W6729676048","https://openalex.org/W6735204497","https://openalex.org/W6735429107","https://openalex.org/W6736155344","https://openalex.org/W6737196085","https://openalex.org/W6738243166","https://openalex.org/W6743150907","https://openalex.org/W6745822563"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W1769849273","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W113247760","https://openalex.org/W2547793174","https://openalex.org/W2132885390","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2544241817"],"abstract_inverted_index":{"Many":[0],"speech":[1,31,124,150],"enhancement":[2,26],"methods":[3,27,146],"try":[4],"to":[5,39],"learn":[6],"the":[7,33,53,58,63,83,88,97,122,131,148],"relationship":[8],"between":[9],"noisy":[10,79],"and":[11,47,67,87,112,118],"clean":[12,30,72,149],"speechs,":[13],"obtained":[14],"using":[15,147],"an":[16,41],"acoustic":[17,46,65],"room":[18],"simulator.":[19],"We":[20,81],"point":[21],"out":[22],"several":[23],"limitations":[24],"of":[25,35,60,71,100,133],"relying":[28],"on":[29,62,77,105],"targets;":[32],"goal":[34],"this":[36],"letter":[37],"is":[38,103],"propose":[40],"alternative":[42],"learning":[43],"algorithm,":[44],"called":[45],"adversarial":[48,94],"supervision":[49],"(AAS).":[50],"AAS":[51,102,136],"makes":[52],"enhanced":[54,123],"output":[55],"both":[56,153],"maximizing":[57],"likelihood":[59],"transcription":[61],"pre-trained":[64],"model":[66],"having":[68],"general":[69],"characteristics":[70],"speech,":[73],"which":[74],"improve":[75],"generalization":[76],"unseen":[78],"speeches.":[80],"employ":[82],"connectionist":[84],"temporal":[85],"classification":[86],"unpaired":[89],"conditional":[90],"boundary":[91],"equilibrium":[92],"generative":[93],"network":[95],"as":[96],"loss":[98,127],"function":[99],"AAS.":[101],"tested":[104],"two":[106],"datasets":[107],"including":[108],"additive":[109],"noise":[110],"without":[111],"with":[113,125],"reverberation,":[114],"Librispeech":[115],"+":[116],"DEMAND,":[117],"CHiME-4.":[119],"By":[120],"visualizing":[121],"different":[126],"combinations,":[128],"we":[129],"demonstrate":[130],"role":[132],"each":[134],"supervision.":[135],"achieves":[137],"a":[138],"lower":[139],"word":[140],"error":[141],"rate":[142],"than":[143],"other":[144],"state-of-the-art":[145],"target":[151],"in":[152],"datasets.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2018-11-16T00:00:00"}