{"id":"https://openalex.org/W2938386503","doi":"https://doi.org/10.1109/icassp.2019.8683092","title":"Mask-based MVDR Beamformer for Noisy Multisource Environments: Introduction of Time-varying Spatial Covariance Model","display_name":"Mask-based MVDR Beamformer for Noisy Multisource Environments: Introduction of Time-varying Spatial Covariance Model","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2938386503","doi":"https://doi.org/10.1109/icassp.2019.8683092","mag":"2938386503"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5102998745","display_name":"Yuki Kubo","orcid":"https://orcid.org/0000-0002-6877-0605"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Kubo","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","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 Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","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 Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"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 Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"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":"Shoko Araki","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6855","last_page":"6859"},"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":0.9988999962806702,"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":0.9969000220298767,"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/beamforming","display_name":"Beamforming","score":0.7157908082008362},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.714705228805542},{"id":"https://openalex.org/keywords/minimum-variance-unbiased-estimator","display_name":"Minimum-variance unbiased estimator","score":0.6477670669555664},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5552541017532349},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5494687557220459},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.5346590280532837},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5149818062782288},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47027474641799927},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.45581477880477905},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.44882872700691223},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3899196684360504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26534563302993774},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2206498086452484},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21098625659942627},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1323850154876709},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11030310392379761},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.06842029094696045},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.06254956126213074}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7157908082008362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.714705228805542},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.6477670669555664},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5552541017532349},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5494687557220459},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.5346590280532837},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5149818062782288},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47027474641799927},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.45581477880477905},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.44882872700691223},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3899196684360504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26534563302993774},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2206498086452484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21098625659942627},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1323850154876709},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11030310392379761},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.06842029094696045},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.06254956126213074},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1503775994","https://openalex.org/W1981463705","https://openalex.org/W1987906574","https://openalex.org/W2024490156","https://openalex.org/W2031583051","https://openalex.org/W2042860487","https://openalex.org/W2043216213","https://openalex.org/W2120608389","https://openalex.org/W2127851351","https://openalex.org/W2143027228","https://openalex.org/W2221409856","https://openalex.org/W2288645994","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2402583539","https://openalex.org/W2489539531","https://openalex.org/W2517616541","https://openalex.org/W2559260703","https://openalex.org/W2702006285","https://openalex.org/W2714509385","https://openalex.org/W2734774145","https://openalex.org/W2750380122","https://openalex.org/W2795131884","https://openalex.org/W2803583024","https://openalex.org/W2891054259","https://openalex.org/W2891997645","https://openalex.org/W2892232131","https://openalex.org/W2962892438"],"related_works":["https://openalex.org/W2033329112","https://openalex.org/W2803318287","https://openalex.org/W2156549393","https://openalex.org/W2171108984","https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W1955763106","https://openalex.org/W2025188156","https://openalex.org/W3002068412"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,7,38,61,76,80,115],"method":[4,77,93],"for":[5,44,78],"designing":[6],"time-varying":[8,39,54,68,81],"minimum":[9],"variance":[10],"distortionless":[11],"response":[12],"(MVDR)":[13],"beamformer":[14,101],"using":[15],"time-frequency":[16],"masks,":[17],"with":[18,114],"the":[19,67,71,86,91,97,100],"aim":[20],"of":[21,47,70,99,104],"improving":[22],"speech":[23,106],"enhancement":[24],"in":[25,102],"noisy":[26],"multi-speaker":[27],"environments.":[28],"A":[29],"key":[30],"to":[31,35],"successful":[32],"beamforming":[33],"is":[34],"estimate":[36],"accurately":[37],"spatial":[40],"covariance":[41],"matrix":[42],"(SCM)":[43],"noise":[45,51,72,82],"composed":[46],"both":[48],"stationary":[49],"diffuse":[50],"and":[52,74,110],"highly":[53],"speech.":[55],"For":[56],"this":[57],"purpose,":[58],"we":[59],"introduce":[60],"stochastic":[62],"model":[63],"that":[64,90],"can":[65,94],"represent":[66],"characteristics":[69],"SCM,":[73],"derive":[75],"estimating":[79],"SCM":[83],"based":[84],"on":[85],"model.":[87],"Experiments":[88],"show":[89],"proposed":[92],"substantially":[95],"improve":[96],"performance":[98],"terms":[103],"automatic":[105],"recognition":[107],"(ASR)":[108],"accuracy":[109],"source-to-distortion":[111],"ratio":[112],"compared":[113],"conventional":[116],"time-invariant":[117],"MVDR":[118],"beamformer.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}