{"id":"https://openalex.org/W2923728956","doi":"https://doi.org/10.1109/taslp.2019.2907015","title":"Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition","display_name":"Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition","publication_year":2019,"publication_date":"2019-03-25","ids":{"openalex":"https://openalex.org/W2923728956","doi":"https://doi.org/10.1109/taslp.2019.2907015","mag":"2923728956"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2907015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2907015","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":"http://hdl.handle.net/2433/240994","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051965288","display_name":"Kazuki Shimada","orcid":"https://orcid.org/0000-0001-5389-2346"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuki Shimada","raw_affiliation_strings":["Kyoto Daigaku, Kyoto, JP"],"raw_orcid":"https://orcid.org/0000-0001-5389-2346","affiliations":[{"raw_affiliation_string":"Kyoto Daigaku, Kyoto, JP","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007353694","display_name":"Yoshiaki Bando","orcid":"https://orcid.org/0000-0002-3934-0745"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoshiaki Bando","raw_affiliation_strings":["Kyoto Daigaku, Kyoto, JP"],"raw_orcid":"https://orcid.org/0000-0002-3934-0745","affiliations":[{"raw_affiliation_string":"Kyoto Daigaku, Kyoto, JP","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["Kyoto Daigaku, Kyoto, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto Daigaku, Kyoto, JP","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003325000","display_name":"Katsutoshi Itoyama","orcid":"https://orcid.org/0000-0002-7098-3896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katsutoshi Itoyama","raw_affiliation_strings":["Kyoto Daigaku, Kyoto, JP"],"raw_orcid":"https://orcid.org/0000-0002-7098-3896","affiliations":[{"raw_affiliation_string":"Kyoto Daigaku, Kyoto, JP","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Kyoto Daigaku, Kyoto, JP"],"raw_orcid":"https://orcid.org/0000-0001-8387-8609","affiliations":[{"raw_affiliation_string":"Kyoto Daigaku, Kyoto, JP","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto Daigaku, Kyoto, JP"],"raw_orcid":"https://orcid.org/0000-0002-2686-2296","affiliations":[{"raw_affiliation_string":"Kyoto Daigaku, Kyoto, JP","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.2169,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.97213681,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"27","issue":"5","first_page":"960","last_page":"971"},"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":0.9987999796867371,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9972000122070312,"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":0.7528661489486694},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7278839945793152},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6983429193496704},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6779303550720215},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.587883472442627},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5493292212486267},{"id":"https://openalex.org/keywords/minimum-variance-unbiased-estimator","display_name":"Minimum-variance unbiased estimator","score":0.5033480525016785},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4859970510005951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4855751395225525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4579003155231476},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.42707258462905884},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3114575743675232},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1866731345653534},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18180730938911438},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.17669793963432312}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7528661489486694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7278839945793152},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6983429193496704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6779303550720215},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.587883472442627},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5493292212486267},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.5033480525016785},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4859970510005951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4855751395225525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4579003155231476},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.42707258462905884},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3114575743675232},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1866731345653534},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18180730938911438},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.17669793963432312},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"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/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":3,"locations":[{"id":"doi:10.1109/taslp.2019.2907015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2907015","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:irdb.nii.ac.jp:01221:0004023139","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/240994","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"},{"id":"pmh:oai:arXiv.org:1903.09341","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.09341","pdf_url":"https://arxiv.org/pdf/1903.09341","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:irdb.nii.ac.jp:01221:0004023139","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/240994","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"},"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"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"},{"id":"https://openalex.org/G2896513494","display_name":"Research of calibration free model for asynchronous distributed microphone array","funder_award_id":"19K12017","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7388475868","display_name":"Automatic speech recognition based on semi-autonomous learning for captioning lectures","funder_award_id":"16H02847","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":59,"referenced_works":["https://openalex.org/W1482149378","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/W2021196544","https://openalex.org/W2058269967","https://openalex.org/W2060108923","https://openalex.org/W2095705004","https://openalex.org/W2112469598","https://openalex.org/W2113990625","https://openalex.org/W2117332620","https://openalex.org/W2127851351","https://openalex.org/W2141998673","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/W2289731793","https://openalex.org/W2326138198","https://openalex.org/W2398042854","https://openalex.org/W2405700021","https://openalex.org/W2412956798","https://openalex.org/W2517616541","https://openalex.org/W2559260703","https://openalex.org/W2586584460","https://openalex.org/W2589857635","https://openalex.org/W2702006285","https://openalex.org/W2714487941","https://openalex.org/W2747798993","https://openalex.org/W2750200823","https://openalex.org/W2762862560","https://openalex.org/W2766672686","https://openalex.org/W2787211894","https://openalex.org/W2804271779","https://openalex.org/W2891378882","https://openalex.org/W2892163332","https://openalex.org/W2922004249","https://openalex.org/W2954695182","https://openalex.org/W2963488660","https://openalex.org/W2987410580","https://openalex.org/W3100968126","https://openalex.org/W4206551434","https://openalex.org/W6631362777","https://openalex.org/W6633895983","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6726313835","https://openalex.org/W6735168207","https://openalex.org/W6743086905","https://openalex.org/W6760722054","https://openalex.org/W6785473800"],"related_works":["https://openalex.org/W2106793170","https://openalex.org/W1577562165","https://openalex.org/W2919389044","https://openalex.org/W2028846388","https://openalex.org/W2072015625","https://openalex.org/W4295210860","https://openalex.org/W1997528538","https://openalex.org/W2777466939","https://openalex.org/W2098233558","https://openalex.org/W4312751558"],"abstract_inverted_index":{"This":[0,115],"paper":[1],"describes":[2],"multichannel":[3,110,189],"speech":[4,9,36,67,105,124,135],"enhancement":[5],"for":[6],"improving":[7],"automatic":[8],"recognition":[10],"(ASR)":[11],"in":[12,82,192,210],"noisy":[13,85,130],"environments.":[14],"Recently,":[15],"the":[16,32,38,102,121,153,164,201,205],"minimum":[17],"variance":[18],"distortionless":[19],"response":[20],"(MVDR)":[21],"beamforming":[22,146,208],"has":[23],"widely":[24],"been":[25],"used":[26],"because":[27],"it":[28],"works":[29],"well":[30],"if":[31],"steering":[33],"vector":[34],"of":[35,43,77,104,123,155,166,172,180,185],"and":[37,106,125,136,150,177,183,187],"spatial":[39,50,173],"covariance":[40],"matrix":[41,112],"(SCM)":[42],"noise":[44,65,107,126,137],"are":[45],"given.":[46],"To":[47,87],"estimating":[48],"such":[49],"information,":[51],"conventional":[52],"studies":[53],"take":[54,92],"a":[55,70],"supervised":[56],"approach":[57,95],"that":[58,96,200,213],"classifies":[59],"each":[60,98],"time-frequency":[61],"(TF)":[62],"bin":[63,100],"into":[64,101],"or":[66],"by":[68,108,147,169],"training":[69,217],"deep":[71],"neural":[72],"network":[73],"(DNN).":[74],"The":[75,196],"performance":[76],"ASR,":[78],"however,":[79],"is":[80,160],"degraded":[81],"an":[83,93],"unknown":[84,211],"environment.":[86],"solve":[88],"this":[89,140],"problem,":[90],"we":[91,142],"unsupervised":[94],"decomposes":[97],"TF":[99],"sum":[103],"using":[109],"nonnegative":[111],"factorization":[113],"(MNMF).":[114],"enables":[116],"us":[117],"to":[118,161],"accurately":[119],"estimate":[120],"SCMs":[122],"not":[127,215],"from":[128,133],"observed":[129],"mixtures":[131],"but":[132],"separated":[134],"components.":[138],"In":[139],"paper,":[141],"propose":[143],"online":[144],"MVDR":[145,181],"effectively":[148],"initializing":[149],"incrementally":[151],"updating":[152],"parameters":[154],"MNMF.":[156,195],"Another":[157],"main":[158],"contribution":[159],"comprehensively":[162],"investigate":[163],"performances":[165],"ASR":[167],"obtained":[168],"various":[170],"types":[171],"filters,":[174,191],"i.e.,":[175],"time-invariant":[176],"variant":[178],"versions":[179],"beamformers":[182],"those":[184],"rank-1":[186],"full-rank":[188],"Wiener":[190],"combination":[193],"with":[194],"experimental":[197],"results":[198],"showed":[199],"proposed":[202],"method":[203,209],"outperformed":[204],"state-of-the-art":[206],"DNN-based":[207],"environments":[212],"did":[214],"match":[216],"data.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}