{"id":"https://openalex.org/W3028504434","doi":"https://doi.org/10.1109/taslp.2020.3013118","title":"Jointly Optimal Denoising, Dereverberation, and Source Separation","display_name":"Jointly Optimal Denoising, Dereverberation, and Source Separation","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3028504434","doi":"https://doi.org/10.1109/taslp.2020.3013118","mag":"3028504434"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3013118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3013118","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,"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"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.09843","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"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":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Corporation, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7487-7150","affiliations":[{"raw_affiliation_string":"NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Christoph Boeddeker","orcid":null},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Boeddeker","raw_affiliation_strings":["Paderborn University, Paderborn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Keisuke Kinoshita","orcid":null},"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":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rintaro Ikeshita","orcid":null},"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":"Rintaro Ikeshita","raw_affiliation_strings":["NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"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":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5175-7834","affiliations":[{"raw_affiliation_string":"NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":null,"display_name":"Reinhold Haeb-Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Paderborn University, Paderborn, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9468-7330","affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8999,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.96235183,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"28","issue":null,"first_page":"2267","last_page":"2282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9926000237464905,"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":0.9926000237464905,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.003000000026077032,"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":0.0019000000320374966,"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/minification","display_name":"Minification","score":0.5618000030517578},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.557200014591217},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.520799994468689},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4586000144481659},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4327999949455261},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4032000005245209},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.36419999599456787},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.3456999957561493},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.34540000557899475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480000257492065},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5777999758720398},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.5618000030517578},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.557200014591217},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4586000144481659},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4327999949455261},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3617999851703644},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.34540000557899475},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.3172999918460846},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C198386975","wikidata":"https://www.wikidata.org/wiki/Q117785","display_name":"Finite impulse response","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2020.3013118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3013118","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,"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:2005.09843","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.09843","pdf_url":"https://arxiv.org/pdf/2005.09843","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:2005.09843","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.09843","pdf_url":"https://arxiv.org/pdf/2005.09843","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W653761051","https://openalex.org/W1983812858","https://openalex.org/W2003203076","https://openalex.org/W2005733316","https://openalex.org/W2014768838","https://openalex.org/W2040782121","https://openalex.org/W2042860487","https://openalex.org/W2044342600","https://openalex.org/W2044893557","https://openalex.org/W2050551142","https://openalex.org/W2060108923","https://openalex.org/W2096819401","https://openalex.org/W2115969105","https://openalex.org/W2130722890","https://openalex.org/W2140571699","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2155638623","https://openalex.org/W2164502538","https://openalex.org/W2168729028","https://openalex.org/W2170768669","https://openalex.org/W2221137476","https://openalex.org/W2221409856","https://openalex.org/W2242685705","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2640112133","https://openalex.org/W2714509385","https://openalex.org/W2734774145","https://openalex.org/W2747732471","https://openalex.org/W2791272514","https://openalex.org/W2800675406","https://openalex.org/W2889503488","https://openalex.org/W2899672738","https://openalex.org/W2905402910","https://openalex.org/W2951130829","https://openalex.org/W2951431217","https://openalex.org/W2952218014","https://openalex.org/W2966098955","https://openalex.org/W2972492143","https://openalex.org/W2972693890","https://openalex.org/W2972728246","https://openalex.org/W2982471419","https://openalex.org/W2989287578","https://openalex.org/W2997453778","https://openalex.org/W2998616931","https://openalex.org/W3015306655","https://openalex.org/W3015661721","https://openalex.org/W4205778870","https://openalex.org/W6608656091","https://openalex.org/W6631362777","https://openalex.org/W6785113001"],"related_works":[],"abstract_inverted_index":{"This":[0,166],"article":[1],"proposes":[2],"methods":[3],"that":[4,147,237],"can":[5,158],"optimize":[6,133],"a":[7,21,26,31,41,117,134,163,170,178,192,202,227],"Convolutional":[8],"BeamFormer":[9],"(CBF)":[10],"for":[11,76,98,112,136,190,221],"jointly":[12,77,113],"performing":[13,137],"denoising,":[14],"dereverberation,":[15],"and":[16,80,93,207,223,263],"source":[17,81],"separation":[18,82],"(DN+DR+SS)":[19],"in":[20,116,250,257,279],"computationally":[22,118],"efficient":[23,121],"way.":[24,122],"Conventionally,":[25],"cascade":[27,255],"configuration,":[28],"composed":[29],"of":[30,55,151,200,214,246,259],"Weighted":[32],"Prediction":[33],"Error":[34],"minimization":[35],"(WPE)":[36],"dereverberation":[37,79],"filter":[38],"followed":[39],"by":[40,173],"Minimum":[42],"Variance":[43],"Distortionless":[44,181],"Response":[45,182],"(MVDR)":[46],"beamformer,":[47],"has":[48,84,94],"been":[49,85,96],"used":[50],"as":[51,177],"the":[52,69,104,148,152,215,238,244,247,253,272,282],"state-of-the-art":[53],"frontend":[54],"far-field":[56],"speech":[57,248],"recognition,":[58],"even":[59],"though":[60],"this":[61,107,124,174],"approach's":[62],"overall":[63],"optimality":[64],"is":[65],"not":[66,95],"guaranteed.":[67],"In":[68],"blind":[70],"signal":[71,260],"processing":[72],"area,":[73],"an":[74,129,145,212],"approach":[75,219],"optimizing":[78,114,191],"(DR+SS)":[83],"proposed;":[86],"however,":[87],"it":[88],"requires":[89],"huge":[90],"computing":[91,273],"cost,":[92],"extended":[97],"applications":[99],"to":[100,132,169],"DN+DR+SS.":[101],"To":[102,123],"overcome":[103],"above":[105],"limitations,":[106],"paper":[108,167],"develops":[109],"new":[110],"approaches":[111,241,268],"DN+DR+SS":[115,138],"much":[119],"more":[120],"end,":[125],"we":[126,186],"first":[127],"present":[128],"objective":[130,175],"function":[131,176],"CBF":[135,171,194,203],"based":[139,195,210,225],"on":[140,144,196,211,226],"maximum":[141],"likelihood":[142],"estimation":[143,277],"assumption":[146],"steering":[149],"vectors":[150],"target":[153],"signals":[154],"are":[155],"given":[156],"or":[157],"be":[159],"estimated,":[160],"e.g.,":[161],"using":[162,231],"neural":[164],"network.":[165],"refers":[168],"optimized":[172],"weighted":[179],"Minimum-Power":[180],"(wMPDR)":[183],"CBF.":[184],"Then,":[185],"derive":[187],"two":[188,197],"algorithms":[189],"wMPDR":[193],"different":[198],"ways":[199],"factorizing":[201],"into":[204],"WPE":[205],"filters":[206],"beamformers:":[208],"one":[209],"extension":[213],"conventional":[216,254,283],"joint":[217,284],"optimization":[218,240,285],"proposed":[220,239,267],"DR+SS":[222],"another":[224],"novel":[228],"technique.":[229],"Experiments":[230],"noisy":[232],"reverberant":[233],"sound":[234],"mixtures":[235],"show":[236],"greatly":[242,270],"improve":[243],"performance":[245],"enhancement":[249],"comparison":[251,280],"with":[252,275,281],"configuration":[256],"terms":[258],"distortion":[261],"measures":[262],"ASR":[264],"performance.":[265],"The":[266],"also":[269],"reduce":[271],"cost":[274],"improved":[276],"accuracy":[278],"approach.":[286]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-05-29T00:00:00"}