{"id":"https://openalex.org/W2402583539","doi":"https://doi.org/10.1109/icassp.2016.7471702","title":"Spatial correlation model based observation vector clustering and MVDR beamforming for meeting recognition","display_name":"Spatial correlation model based observation vector clustering and MVDR beamforming for meeting recognition","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2402583539","doi":"https://doi.org/10.1109/icassp.2016.7471702","mag":"2402583539"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471702","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/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 Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036258898","display_name":"Masahiro Okada","orcid":"https://orcid.org/0000-0002-6896-8419"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]},{"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":"Masahiro Okada","raw_affiliation_strings":["Graduate School of Design, Kyushu University, Fukuoka, Japan","NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Design, Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]},{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101768343","display_name":"Takuya Higuchi","orcid":"https://orcid.org/0000-0002-0361-7132"},"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":"Takuya Higuchi","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"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":"Atsunori Ogawa","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","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 Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.1262,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.97003811,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"385","last_page":"389"},"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":0.996399998664856,"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":0.9962999820709229,"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":0.77585768699646},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7211678624153137},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.7105613946914673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6958991885185242},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6588553190231323},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6061262488365173},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.580380380153656},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4893750548362732},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.4453516900539398},{"id":"https://openalex.org/keywords/minimum-variance-unbiased-estimator","display_name":"Minimum-variance unbiased estimator","score":0.44020816683769226},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.434115469455719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39617493748664856},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3750097155570984},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2578662037849426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18105849623680115},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.1533803939819336},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10595008730888367},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.08776205778121948},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0845334529876709}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.77585768699646},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7211678624153137},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.7105613946914673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6958991885185242},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6588553190231323},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6061262488365173},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.580380380153656},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4893750548362732},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.4453516900539398},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.44020816683769226},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.434115469455719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39617493748664856},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3750097155570984},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2578662037849426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18105849623680115},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.1533803939819336},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10595008730888367},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.08776205778121948},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0845334529876709},{"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.2016.7471702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471702","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1554827512","https://openalex.org/W1558643924","https://openalex.org/W1934041838","https://openalex.org/W1983812858","https://openalex.org/W2002146237","https://openalex.org/W2003203076","https://openalex.org/W2005733316","https://openalex.org/W2025344720","https://openalex.org/W2036365100","https://openalex.org/W2093554785","https://openalex.org/W2143027228","https://openalex.org/W2145167175","https://openalex.org/W2153773386","https://openalex.org/W2288645994","https://openalex.org/W2394967684","https://openalex.org/W2400339399","https://openalex.org/W3141933106","https://openalex.org/W6633067235","https://openalex.org/W6633348054","https://openalex.org/W6659344013","https://openalex.org/W6681537870","https://openalex.org/W6711908631"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2380771148","https://openalex.org/W2900122540","https://openalex.org/W2396048001","https://openalex.org/W4240587264","https://openalex.org/W2348931051","https://openalex.org/W2011788874"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"a":[3,19,76,99,123],"minimum":[4],"variance":[5],"distortionless":[6],"response":[7],"(MVDR)":[8],"beamforming":[9],"based":[10,119],"speech":[11,16,120],"enhancement":[12,121],"approach":[13],"for":[14],"meeting":[15,20,124],"recognition.":[17],"In":[18],"situation,":[21],"speaker":[22],"overlaps":[23],"and":[24],"noise":[25,68],"signals":[26],"are":[27],"not":[28],"negligible.":[29],"To":[30],"handle":[31],"these":[32],"issues,":[33],"we":[34],"employ":[35],"MVDR":[36,114],"beamforming,":[37],"where":[38],"accurate":[39],"estimation":[40,53],"of":[41,59,83,94],"the":[42,56,79,91,95,112],"steering":[43,51],"vector":[44,52],"is":[45,72,87],"paramount.":[46],"We":[47],"recently":[48],"found":[49],"that":[50,111],"by":[54,74,89],"clustering":[55,71],"time-frequency":[57,92],"components":[58,93],"microphone":[60],"observation":[61,96],"vectors":[62,97],"performs":[63],"well":[64],"as":[65],"regards":[66],"real-world":[67],"reduction.":[69],"The":[70],"performed":[73],"taking":[75],"cue":[77],"from":[78],"spatial":[80],"correlation":[81],"matrix":[82],"each":[84],"speaker,":[85],"which":[86],"realized":[88],"modeling":[90],"with":[98,107],"complex":[100],"Gaussian":[101],"mixture":[102],"model":[103],"(CGMM).":[104],"Experimental":[105],"results":[106],"real":[108],"recordings":[109],"show":[110],"proposed":[113],"scheme":[115],"outperforms":[116],"conventional":[117],"null-beamformer":[118],"in":[122],"situation.":[125]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}