{"id":"https://openalex.org/W2586584460","doi":"https://doi.org/10.1109/taslp.2017.2665341","title":"Online MVDR Beamformer Based on Complex Gaussian Mixture Model With Spatial Prior for Noise Robust ASR","display_name":"Online MVDR Beamformer Based on Complex Gaussian Mixture Model With Spatial Prior for Noise Robust ASR","publication_year":2017,"publication_date":"2017-02-07","ids":{"openalex":"https://openalex.org/W2586584460","doi":"https://doi.org/10.1109/taslp.2017.2665341","mag":"2586584460"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2665341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2665341","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":["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/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 Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101438174","display_name":"Nobutaka Ito","orcid":"https://orcid.org/0000-0001-9740-6848"},"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":"Nobutaka Ito","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","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, Nippon Telegraph and Telephone Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"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 Yoshioka","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone 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, Nippon Telegraph and Telephone Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, 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 Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":10.2299,"has_fulltext":false,"cited_by_count":112,"citation_normalized_percentile":{"value":0.98827435,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"25","issue":"4","first_page":"780","last_page":"793"},"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":0.9994999766349792,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.7031025290489197},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6594053506851196},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6378117203712463},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5783805251121521},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5715732574462891},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5336718559265137},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5095387101173401},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.44594162702560425},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3468918800354004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30630794167518616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16676798462867737},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1358325481414795},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11513978242874146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7031025290489197},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6594053506851196},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6378117203712463},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5783805251121521},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5715732574462891},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5336718559265137},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5095387101173401},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.44594162702560425},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3468918800354004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30630794167518616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16676798462867737},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1358325481414795},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11513978242874146},{"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/taslp.2017.2665341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2665341","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1543386260","https://openalex.org/W1555217905","https://openalex.org/W1799366690","https://openalex.org/W1934041838","https://openalex.org/W1935589317","https://openalex.org/W1981463705","https://openalex.org/W1985261152","https://openalex.org/W1987906574","https://openalex.org/W1995562189","https://openalex.org/W2003203076","https://openalex.org/W2005733316","https://openalex.org/W2027884847","https://openalex.org/W2031583051","https://openalex.org/W2033310064","https://openalex.org/W2042860487","https://openalex.org/W2043216213","https://openalex.org/W2096855653","https://openalex.org/W2097221914","https://openalex.org/W2099984896","https://openalex.org/W2100335648","https://openalex.org/W2101169486","https://openalex.org/W2101609516","https://openalex.org/W2106310986","https://openalex.org/W2143027228","https://openalex.org/W2166692540","https://openalex.org/W2168729028","https://openalex.org/W2170222430","https://openalex.org/W2185726469","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2400339399","https://openalex.org/W2402583539","https://openalex.org/W2534981247","https://openalex.org/W2616139854","https://openalex.org/W6607333740","https://openalex.org/W6638444622","https://openalex.org/W6674864272","https://openalex.org/W6686651311"],"related_works":["https://openalex.org/W1980381208","https://openalex.org/W2364594919","https://openalex.org/W2963170046","https://openalex.org/W2376244802","https://openalex.org/W1861706286","https://openalex.org/W4311414679","https://openalex.org/W2219338811","https://openalex.org/W2923631784","https://openalex.org/W818226659","https://openalex.org/W2167092671"],"abstract_inverted_index":{"This":[0,134,158],"paper":[1,135],"considers":[2],"acoustic":[3],"beamforming":[4],"for":[5,36,54,88,140,186],"noise":[6,15,38,222,247],"robust":[7],"automatic":[8],"speech":[9,71,100,127,282],"recognition.":[10],"A":[11],"beamformer":[12,96,215],"attenuates":[13],"background":[14],"by":[16,25],"enhancing":[17],"sound":[18],"components":[19],"coming":[20],"from":[21,172,260],"a":[22,26,55,62,70,76,113,120,154,182,187,265,279],"direction":[23],"specified":[24],"steering":[27,31,49,89,198],"vector.":[28],"Hence,":[29],"accurate":[30],"vector":[32,90,199],"estimation":[33,200],"is":[34],"paramount":[35],"successful":[37],"reduction.":[39],"Recently,":[40],"time-frequency":[41,85],"masking":[42],"has":[43],"been":[44],"proposed":[45,109,115,213],"to":[46,82,97,148,174,243,246,262],"estimate":[47,83],"the":[48,84,94,108,125,131,162,169,202,209,212,227,230,239,254,258,271,275],"vectors":[50],"that":[51,107,149,219,253],"are":[52],"used":[53],"beamformer.":[56],"In":[57,207],"particular,":[58],"we":[59,180],"have":[60],"developed":[61],"new":[63],"form":[64],"of":[65,130,150,204,211,226,229],"this":[66,178],"approach,":[67],"which":[68,144,194],"uses":[69],"spectral":[72],"model":[73,80,123],"based":[74,118],"on":[75,119,168],"complex":[77],"Gaussian":[78],"mixture":[79,122],"(CGMM)":[81],"masks":[86],"needed":[87],"estimation,":[91],"and":[92,124,277],"extended":[93],"CGMM-based":[95,110,272],"an":[98],"online":[99,142,159,214,281],"enhancement":[101,128,283],"scenario.":[102],"Our":[103],"previous":[104],"experiments":[105],"showed":[106],"approach":[111,273],"outperforms":[112,278],"recently":[114],"mask":[116],"estimator":[117],"Watson":[121],"baseline":[126],"system":[129],"CHiME-3":[132,163],"challenge.":[133],"provides":[136],"additional":[137],"experimental":[138],"results":[139,251],"our":[141],"processing,":[143],"achieves":[145],"performance":[146,210],"comparable":[147],"batch":[151],"processing":[152],"with":[153,217,270],"suitable":[155],"block-batch":[156],"size.":[157],"version":[160],"reduces":[161,257],"word":[164],"error":[165],"rate":[166],"(WER)":[167],"evaluation":[170],"set":[171],"8.37%":[173],"8.06%.":[175],"Moreover,":[176],"in":[177,201,264],"paper,":[179],"introduce":[181],"probabilistic":[183],"prior":[184,237,256],"distribution":[185],"spatial":[188,236,255],"correlation":[189],"matrix":[190],"(a":[191],"CGMM":[192,231],"parameter),":[193],"enables":[195,238],"more":[196],"stable":[197],"presence":[203],"interfering":[205],"speakers.":[206],"practice,":[208],"degrades":[216],"observations":[218],"contain":[220],"only":[221],"or/and":[223,248],"interference":[224],"because":[225],"failure":[228],"parameter":[232,242],"estimation.":[233],"The":[234],"introduced":[235],"target":[240],"speaker's":[241],"avoid":[244],"overfitting":[245],"interference.":[249],"Experimental":[250],"show":[252],"WER":[259],"38.4%":[261],"29.2%":[263],"conversation":[266],"recognition":[267],"task":[268],"compared":[269],"without":[274],"prior,":[276],"conventional":[280],"approach.":[284]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}