{"id":"https://openalex.org/W3122264812","doi":"https://doi.org/10.23919/eusipco54536.2021.9616166","title":"Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech","display_name":"Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3122264812","doi":"https://doi.org/10.23919/eusipco54536.2021.9616166","mag":"3122264812"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616166","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616166","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"article","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/A5005224645","display_name":"Takuya Fujimura","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142609","display_name":"National Institute of Technology, Tokuyama College","ror":"https://ror.org/046jx2h22","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210120810","https://openalex.org/I4210142609"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takuya Fujimura","raw_affiliation_strings":["National Institute of Technology, Tokuyama College, Yamaguchi, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Technology, Tokuyama College, Yamaguchi, Japan","institution_ids":["https://openalex.org/I4210142609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuma Koizumi","raw_affiliation_strings":["NTT Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034837951","display_name":"Kohei Yatabe","orcid":"https://orcid.org/0000-0002-1345-0663"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Yatabe","raw_affiliation_strings":["Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075732053","display_name":"Ryoichi Miyazaki","orcid":"https://orcid.org/0000-0002-5023-5380"},"institutions":[{"id":"https://openalex.org/I4210142609","display_name":"National Institute of Technology, Tokuyama College","ror":"https://ror.org/046jx2h22","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210120810","https://openalex.org/I4210142609"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryoichi Miyazaki","raw_affiliation_strings":["National Institute of Technology, Tokuyama College, Yamaguchi, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Technology, Tokuyama College, Yamaguchi, Japan","institution_ids":["https://openalex.org/I4210142609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005224645"],"corresponding_institution_ids":["https://openalex.org/I4210142609"],"apc_list":null,"apc_paid":null,"fwci":6.3697,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.98989218,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"436","last_page":"440"},"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":0.9995999932289124,"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":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8118511438369751},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.709198534488678},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.635562002658844},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5933338403701782},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5252962708473206},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4993867874145508},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4968099892139435},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4582170844078064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.410236120223999},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3562929034233093},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.11091634631156921}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8118511438369751},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.709198534488678},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.635562002658844},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5933338403701782},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5252962708473206},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4993867874145508},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4968099892139435},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4582170844078064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.410236120223999},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3562929034233093},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.11091634631156921},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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:10.23919/eusipco54536.2021.9616166","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616166","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1974387177","https://openalex.org/W1983108229","https://openalex.org/W2094721231","https://openalex.org/W2141411743","https://openalex.org/W2144404214","https://openalex.org/W2187089797","https://openalex.org/W2289394825","https://openalex.org/W2526050071","https://openalex.org/W2603567530","https://openalex.org/W2793146153","https://openalex.org/W2884797218","https://openalex.org/W2924514313","https://openalex.org/W2954695182","https://openalex.org/W2962760690","https://openalex.org/W2962866211","https://openalex.org/W2964121744","https://openalex.org/W2964204553","https://openalex.org/W2972359262","https://openalex.org/W2982346427","https://openalex.org/W3015219411","https://openalex.org/W3016050488","https://openalex.org/W3032502780","https://openalex.org/W3036069164","https://openalex.org/W3087443678","https://openalex.org/W3127686677","https://openalex.org/W4298091485","https://openalex.org/W6749271710","https://openalex.org/W6779341498","https://openalex.org/W6779963951"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W3110551121","https://openalex.org/W3160071434","https://openalex.org/W2131486661","https://openalex.org/W4200596008"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"(DNN)-based":[3],"speech":[4,9,40,49,110],"enhancement":[5,41],"ordinarily":[6],"requires":[7],"clean":[8,17,55,74,91,135],"signals":[10,18,75,99,111],"as":[11],"the":[12,34,58,67,71,113,120,125],"training":[13,37,61,85],"target.":[14],"However,":[15],"collecting":[16],"is":[19,63],"very":[20],"costly":[21],"because":[22],"they":[23],"must":[24],"be":[25,77],"recorded":[26],"in":[27,112],"a":[28,84,107,131],"studio.":[29],"This":[30],"requirement":[31,72],"currently":[32],"restricts":[33],"amount":[35,59],"of":[36,46,48,60,73,109,130],"data":[38,62],"for":[39,65,100],"to":[42,105,128],"less":[43],"than":[44],"1/1000":[45],"that":[47,87,119,129],"recognition":[50],"which":[51,102],"does":[52,88],"not":[53,89],"need":[54],"signals.":[56,92,136],"Increasing":[57],"important":[64],"improving":[66],"performance,":[68],"and":[69],"hence":[70],"should":[76],"relaxed.":[78],"In":[79],"this":[80],"paper,":[81],"we":[82],"propose":[83],"strategy":[86],"require":[90],"The":[93],"proposed":[94,121],"method":[95,122],"only":[96],"utilizes":[97],"noisy":[98],"training,":[101],"enables":[103],"us":[104],"use":[106],"variety":[108],"wild.":[114],"Our":[115],"experimental":[116],"results":[117],"showed":[118],"can":[123],"achieve":[124],"performance":[126],"similar":[127],"DNN":[132],"trained":[133],"with":[134]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":4}],"updated_date":"2026-04-19T06:08:04.723047","created_date":"2025-10-10T00:00:00"}