{"id":"https://openalex.org/W2891378882","doi":"https://doi.org/10.1109/icassp.2018.8462642","title":"Unsupervised Beamforming Based on Multichannel Nonnegative Matrix Factorization for Noisy Speech Recognition","display_name":"Unsupervised Beamforming Based on Multichannel Nonnegative Matrix Factorization for Noisy Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891378882","doi":"https://doi.org/10.1109/icassp.2018.8462642","mag":"2891378882"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462642","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/A5051965288","display_name":"Kazuki Shimada","orcid":"https://orcid.org/0000-0001-5389-2346"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuki Shimada","raw_affiliation_strings":["Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan","Kyoto University, School of Informatics, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, School of Informatics, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["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/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiaki Bando","raw_affiliation_strings":["Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan","Kyoto University, School of Informatics, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, School of Informatics, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan","Kyoto University, School of Informatics, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, School of Informatics, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003325000","display_name":"Katsutoshi Itoyama","orcid":"https://orcid.org/0000-0002-7098-3896"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsutoshi Itoyama","raw_affiliation_strings":["Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan","Kyoto University, School of Informatics, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, School of Informatics, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan","Kyoto University, School of Informatics, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, School of Informatics, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan","Kyoto University, School of Informatics, Sakyo-ku, Kyoto 606-8501, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, School of Informatics, Sakyo-ku, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5734","last_page":"5738"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9983999729156494,"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":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.8250770568847656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6746073961257935},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.611204981803894},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.606992244720459},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6012305021286011},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.510503888130188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4916077256202698},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4791618883609772},{"id":"https://openalex.org/keywords/minimum-variance-unbiased-estimator","display_name":"Minimum-variance unbiased estimator","score":0.478253036737442},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.46730729937553406},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.42826375365257263},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.42380034923553467},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2531595230102539},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2365381121635437},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.14230424165725708},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.127652108669281},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09986275434494019},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08073613047599792},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06640374660491943}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.8250770568847656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6746073961257935},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.611204981803894},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.606992244720459},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6012305021286011},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.510503888130188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4916077256202698},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4791618883609772},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.478253036737442},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.46730729937553406},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.42826375365257263},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.42380034923553467},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2531595230102539},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2365381121635437},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.14230424165725708},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.127652108669281},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09986275434494019},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08073613047599792},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06640374660491943},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462642","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1502984613","https://openalex.org/W1524333225","https://openalex.org/W1570694229","https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W1993882792","https://openalex.org/W2005522781","https://openalex.org/W2016100027","https://openalex.org/W2060108923","https://openalex.org/W2074307898","https://openalex.org/W2095705004","https://openalex.org/W2113519555","https://openalex.org/W2113990625","https://openalex.org/W2122635992","https://openalex.org/W2143027228","https://openalex.org/W2147768505","https://openalex.org/W2148613904","https://openalex.org/W2158143227","https://openalex.org/W2168273590","https://openalex.org/W2168729028","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2412956798","https://openalex.org/W2517616541","https://openalex.org/W2559260703","https://openalex.org/W2702006285","https://openalex.org/W2714487941","https://openalex.org/W2747798993","https://openalex.org/W2750200823","https://openalex.org/W2949117887","https://openalex.org/W2954695182","https://openalex.org/W6630257147","https://openalex.org/W6631362777","https://openalex.org/W6633895983","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6654629877","https://openalex.org/W6668898254","https://openalex.org/W6674330103","https://openalex.org/W6735168207","https://openalex.org/W6739644732","https://openalex.org/W6740340063","https://openalex.org/W6743621323"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W2037504162","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2539013788","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2075222291","https://openalex.org/W2900450731"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"unsupervised":[3,83],"multichannel":[4,93,142],"speech":[5,9,29,58,107],"enhancement":[6],"for":[7,19,33,49,98,120],"noisy":[8],"recognition.":[10],"Time-frequency":[11],"(TF)":[12],"mask":[13,39],"estimation":[14,40],"has":[15],"actively":[16],"been":[17],"studied":[18],"estimating":[20],"the":[21,51,77,104,109,131,156,168],"steering":[22],"vectors":[23],"and":[24,30,59,108,127],"spatial":[25,78],"covariance":[26,79],"matrices":[27,80],"of":[28,54,106,118,130],"noise":[31],"used":[32],"beamforming.":[34],"The":[35,146],"state-of-the-art":[36,157],"approach":[37,154],"to":[38,42,140],"is":[41],"use":[43],"deep":[44],"neural":[45],"networks":[46],"(DNN":[47],"s)":[48],"classifying":[50],"TF":[52,101],"bins":[53],"observed":[55],"signals":[56],"into":[57,103],"noise.":[60],"Such":[61],"a":[62,115],"supervised":[63],"approach,":[64],"however,":[65],"does":[66],"not":[67,166],"work":[68],"well":[69],"in":[70,81,138,161],"an":[71,82],"unknown":[72,162],"environment.":[73],"To":[74,113],"accurately":[75],"estimate":[76],"manner,":[84],"we":[85,122],"perform":[86],"blind":[87],"source":[88],"separation":[89],"(BSS)":[90],"based":[91],"on":[92],"nonnegative":[94],"matrix":[95],"factorization":[96],"(MNMF)":[97],"decomposing":[99],"each":[100],"bin":[102],"components":[105],"other":[110],"sources":[111],"(noise).":[112],"clarify":[114],"suitable":[116],"type":[117],"beamforming":[119,137,153,159],"MNMF,":[121],"tested":[123],"both":[124],"time-":[125],"invariant":[126],"time-varying":[128],"versions":[129],"minimum":[132],"variance":[133],"distortionless":[134],"response":[135],"(MVDR)":[136],"addition":[139],"standard":[141],"Wiener":[143],"filtering":[144],"(MWF).":[145],"experimental":[147],"results":[148],"showed":[149],"that":[150,164],"our":[151],"MNMF-based":[152],"outperformed":[155],"DNN-based":[158],"method":[160],"environments":[163],"do":[165],"match":[167],"training":[169],"data.":[170]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}