{"id":"https://openalex.org/W2979850772","doi":"https://doi.org/10.1109/taslp.2019.2944348","title":"Semi-Supervised Multichannel Speech Enhancement With a Deep Speech Prior","display_name":"Semi-Supervised Multichannel Speech Enhancement With a Deep Speech Prior","publication_year":2019,"publication_date":"2019-10-07","ids":{"openalex":"https://openalex.org/W2979850772","doi":"https://doi.org/10.1109/taslp.2019.2944348","mag":"2979850772"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2944348","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2944348","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/taslp.2019.2944348","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069659508","display_name":"Kouhei Sekiguchi","orcid":"https://orcid.org/0000-0001-6160-9301"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kouhei Sekiguchi","raw_affiliation_strings":["Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6160-9301","affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007353694","display_name":"Yoshiaki Bando","orcid":"https://orcid.org/0000-0002-3934-0745"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiaki Bando","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3934-0745","affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082272880","display_name":"Aditya Arie Nugraha","orcid":"https://orcid.org/0000-0001-5424-747X"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aditya Arie Nugraha","raw_affiliation_strings":["Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5424-747X","affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8387-8609","affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto"],"raw_orcid":"https://orcid.org/0000-0002-2686-2296","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7438,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.96008285,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"27","issue":"12","first_page":"2197","last_page":"2212"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.996999979019165,"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/speech-enhancement","display_name":"Speech enhancement","score":0.7296913266181946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7148901224136353},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6806704998016357},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6581802368164062},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5772768259048462},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5573928952217102},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.5559334754943848},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5151132941246033},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.45511558651924133},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4047783315181732},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40424880385398865},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1907815933227539},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17044097185134888},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.12248978018760681},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.09138616919517517},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07392850518226624}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7296913266181946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7148901224136353},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6806704998016357},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6581802368164062},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5772768259048462},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5573928952217102},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.5559334754943848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5151132941246033},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45511558651924133},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4047783315181732},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40424880385398865},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1907815933227539},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17044097185134888},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.12248978018760681},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.09138616919517517},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07392850518226624},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2019.2944348","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2944348","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2019.2944348","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2944348","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.800000011920929}],"awards":[{"id":"https://openalex.org/G1688345242","display_name":"Next generation speech translation research","funder_award_id":"17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1902027874","https://openalex.org/W1959608418","https://openalex.org/W1985093013","https://openalex.org/W2003203076","https://openalex.org/W2039844283","https://openalex.org/W2054221677","https://openalex.org/W2060108923","https://openalex.org/W2072548008","https://openalex.org/W2113990625","https://openalex.org/W2114461480","https://openalex.org/W2117332620","https://openalex.org/W2124149378","https://openalex.org/W2127851351","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2148613904","https://openalex.org/W2158291955","https://openalex.org/W2160547390","https://openalex.org/W2168273590","https://openalex.org/W2326138198","https://openalex.org/W2398042854","https://openalex.org/W2405774341","https://openalex.org/W2407685581","https://openalex.org/W2408744528","https://openalex.org/W2412956798","https://openalex.org/W2517616541","https://openalex.org/W2559809918","https://openalex.org/W2746457594","https://openalex.org/W2746904187","https://openalex.org/W2766672686","https://openalex.org/W2787211894","https://openalex.org/W2804271779","https://openalex.org/W2883322837","https://openalex.org/W2892163332","https://openalex.org/W2901552243","https://openalex.org/W2903219940","https://openalex.org/W2922004249","https://openalex.org/W2923728956","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963969588","https://openalex.org/W2964121744","https://openalex.org/W3100968126","https://openalex.org/W3121132363","https://openalex.org/W4206551434","https://openalex.org/W4292691288","https://openalex.org/W4391602018","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6713658392","https://openalex.org/W6714030504"],"related_works":["https://openalex.org/W2101428145","https://openalex.org/W2130715307","https://openalex.org/W2338894643","https://openalex.org/W2055537285","https://openalex.org/W2002519017","https://openalex.org/W2003780581","https://openalex.org/W3023185158","https://openalex.org/W1538254361","https://openalex.org/W1914599625","https://openalex.org/W2900450731"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,67,72,79,87,91,96],"semi-supervised":[4],"multichannel":[5,18,126],"speech":[6,12,39,69,75,84,89,105,110,116,128,140,192],"enhancement":[7],"method":[8,160],"that":[9,153,173],"uses":[10],"clean":[11,115],"data":[13,117],"for":[14,37],"prior":[15],"training.":[16],"Although":[17],"nonnegative":[19],"matrix":[20,30],"factorization":[21],"(MNMF)":[22],"and":[23,54,95,106,137,141,167,176],"its":[24],"constrained":[25],"variant":[26],"called":[27],"independent":[28],"low-rank":[29,42,68,92],"analysis":[31],"(ILRMA)":[32],"have":[33],"successfully":[34],"been":[35],"used":[36],"unsupervised":[38,120,147],"enhancement,":[40],"the":[41,45,130,154,158,168,174,190],"assumption":[43],"on":[44],"power":[46],"spectral":[47],"densities":[48],"(PSDs)":[49],"of":[50,82,101,104,139,157,179],"all":[51],"sources":[52],"(speech":[53],"noise)":[55],"does":[56],"not":[57],"hold":[58],"in":[59,118,145],"reality.":[60],"To":[61],"solve":[62],"this":[63],"problem,":[64],"we":[65],"replace":[66],"model":[70,81,100,111],"with":[71,181],"deep":[73,88,109],"generative":[74],"model,":[76,90,94],"i.e.,":[77],"formulate":[78],"probabilistic":[80],"noisy":[83,127],"by":[85,188],"integrating":[86],"noise":[93,142],"full-rank":[97,131,155],"or":[98,132],"rank-1":[99,133,169],"spatial":[102,134,183],"characteristics":[103],"noise.":[107],"The":[108],"is":[112],"trained":[113],"from":[114],"an":[119,146],"auto-encoding":[121],"variational":[122],"Bayesian":[123],"manner.":[124,149],"Given":[125],"spectra,":[129],"covariance":[135],"matrices":[136],"PSDs":[138],"are":[143],"estimated":[144],"maximum-likelihood":[148],"Experimental":[150],"results":[151],"showed":[152],"version":[156],"proposed":[159],"was":[161],"significantly":[162],"better":[163],"than":[164],"MNMF,":[165],"ILRMA,":[166],"version.":[170],"We":[171],"confirmed":[172],"initialization-sensitivity":[175],"local-optimum":[177],"problems":[178],"MNMF":[180],"many":[182],"parameters":[184],"can":[185],"be":[186],"solved":[187],"incorporating":[189],"precise":[191],"model.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-09T07:52:08.696243","created_date":"2025-10-10T00:00:00"}