{"id":"https://openalex.org/W2400339399","doi":"https://doi.org/10.1109/icassp.2016.7472671","title":"Robust MVDR beamforming using time-frequency masks for online/offline ASR in noise","display_name":"Robust MVDR beamforming using time-frequency masks for online/offline ASR in noise","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2400339399","doi":"https://doi.org/10.1109/icassp.2016.7472671","mag":"2400339399"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472671","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":"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/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, 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/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, 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/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, 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/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"]}]}],"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":null,"has_fulltext":false,"cited_by_count":189,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5210","last_page":"5214"},"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.8056332468986511},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7670344114303589},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6898094415664673},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6502150297164917},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5847156047821045},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4804510772228241},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.46080848574638367},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43059882521629333},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4115332365036011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3439287543296814},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11439454555511475},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10564115643501282}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.8056332468986511},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670344114303589},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6898094415664673},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6502150297164917},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5847156047821045},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4804510772228241},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.46080848574638367},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43059882521629333},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4115332365036011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3439287543296814},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11439454555511475},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10564115643501282},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472671","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":0.5400000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1555217905","https://openalex.org/W1799366690","https://openalex.org/W1935589317","https://openalex.org/W1985261152","https://openalex.org/W1987906574","https://openalex.org/W1995562189","https://openalex.org/W2003203076","https://openalex.org/W2031583051","https://openalex.org/W2033310064","https://openalex.org/W2042860487","https://openalex.org/W2043216213","https://openalex.org/W2099984896","https://openalex.org/W2100335648","https://openalex.org/W2143027228","https://openalex.org/W2168729028","https://openalex.org/W2170222430","https://openalex.org/W2171784699","https://openalex.org/W2185726469","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2534981247","https://openalex.org/W2616139854","https://openalex.org/W6638444622","https://openalex.org/W6674864272"],"related_works":["https://openalex.org/W2401089611","https://openalex.org/W3108403339","https://openalex.org/W2022538999","https://openalex.org/W2162712524","https://openalex.org/W1955763106","https://openalex.org/W2002243964","https://openalex.org/W2023005931","https://openalex.org/W2142924612","https://openalex.org/W3171883019","https://openalex.org/W4287867034"],"abstract_inverted_index":{"This":[0,97,153],"paper":[1,98],"considers":[2],"acoustic":[3],"beamforming":[4,43],"for":[5,37,107],"noise":[6,16,39],"robust":[7],"automatic":[8],"speech":[9,53,73,138],"recognition":[10,54,151],"(ASR).":[11],"A":[12],"beamformer":[13],"attenuates":[14],"background":[15],"by":[17,26,174],"enhancing":[18],"sound":[19],"components":[20],"coming":[21],"from":[22,162],"a":[23,27,42,64,72,78,117,124,168],"direction":[24],"specified":[25],"steering":[28,32,91],"vector.":[29],"Hence,":[30],"accurate":[31],"vector":[33,92],"estimation":[34],"is":[35,133,167],"paramount":[36],"successful":[38],"reduction.":[40],"Recently,":[41],"approach":[44,69,115,132],"was":[45],"proposed":[46,119],"that":[47,70,112,172],"employs":[48],"time-frequency":[49,87],"masks.":[50],"In":[51,128],"the":[52,59,86,90,113,130,157],"system":[55],"we":[56,62],"submitted":[57],"to":[58,84,135,145,164,171],"CHiME-3":[60,158],"Challenge,":[61],"employed":[63],"new":[65],"form":[66],"of":[67],"this":[68,101,143],"uses":[71],"spectral":[74],"model":[75,82],"based":[76,122],"on":[77,100,123],"complex":[79],"Gaussian":[80],"mixture":[81,126],"(CGMM)":[83],"estimate":[85],"masks":[88],"and":[89,103],"without":[93],"providing":[94],"technical":[95],"details.":[96],"elaborates":[99],"technique":[102,144],"examines":[104],"its":[105],"effectiveness":[106],"ASR.":[108],"Experimental":[109],"results":[110],"show":[111],"CGMM-based":[114,131],"outperforms":[116],"recently":[118],"mask":[120],"estimator":[121],"Watson":[125],"model.":[127],"addition,":[129],"extended":[134],"an":[136,149],"online":[137,150,154],"enhancement":[139],"scenario,":[140],"which":[141,166],"allows":[142],"be":[146],"used":[147],"in":[148],"setup.":[152],"version":[155],"reduces":[156],"evaluation":[159],"error":[160],"rate":[161],"15.60%":[163],"8.47%,":[165],"comparable":[169],"improvement":[170],"obtained":[173],"batch":[175],"processing.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":30},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}