{"id":"https://openalex.org/W3163391314","doi":"https://doi.org/10.1109/icassp39728.2021.9414264","title":"Blind and Neural Network-Guided Convolutional Beamformer for Joint Denoising, Dereverberation, and Source Separation","display_name":"Blind and Neural Network-Guided Convolutional Beamformer for Joint Denoising, Dereverberation, and Source Separation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163391314","doi":"https://doi.org/10.1109/icassp39728.2021.9414264","mag":"3163391314"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.01836","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084590882","display_name":"Rintaro Ikeshita","orcid":"https://orcid.org/0000-0003-2608-1999"},"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":"Rintaro Ikeshita","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, 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 Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007032557","display_name":"Hiroshi Sawada","orcid":"https://orcid.org/0000-0002-4831-9286"},"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":"Hiroshi Sawada","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, 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 Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, 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":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6129","last_page":"6133"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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":0.8030173778533936},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.7397157549858093},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6211844086647034},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5612255930900574},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5411171317100525},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5075875520706177},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4961150586605072},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4897024929523468},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.47739213705062866},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46197429299354553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4531576335430145},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44395753741264343},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43263566493988037},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3251023292541504},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12359380722045898},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06429147720336914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8030173778533936},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.7397157549858093},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6211844086647034},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5612255930900574},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5411171317100525},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5075875520706177},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4961150586605072},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4897024929523468},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.47739213705062866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46197429299354553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4531576335430145},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44395753741264343},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43263566493988037},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3251023292541504},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12359380722045898},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06429147720336914},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.01836","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.01836","pdf_url":"https://arxiv.org/pdf/2108.01836","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:arXiv.org:2108.01836","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.01836","pdf_url":"https://arxiv.org/pdf/2108.01836","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W108815450","https://openalex.org/W1482149378","https://openalex.org/W1524333225","https://openalex.org/W1543386260","https://openalex.org/W1548802052","https://openalex.org/W2014768838","https://openalex.org/W2031583051","https://openalex.org/W2042860487","https://openalex.org/W2043216213","https://openalex.org/W2099741732","https://openalex.org/W2107992675","https://openalex.org/W2114461480","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2164502538","https://openalex.org/W2170768669","https://openalex.org/W2242685705","https://openalex.org/W2408744528","https://openalex.org/W2563666542","https://openalex.org/W2640112133","https://openalex.org/W2702006285","https://openalex.org/W2747732471","https://openalex.org/W2800675406","https://openalex.org/W2951431217","https://openalex.org/W2952218014","https://openalex.org/W2954049404","https://openalex.org/W2963375116","https://openalex.org/W2972492143","https://openalex.org/W2972693890","https://openalex.org/W2997453778","https://openalex.org/W2997688633","https://openalex.org/W3028504434","https://openalex.org/W3096073522","https://openalex.org/W3096752279","https://openalex.org/W3099177480","https://openalex.org/W3099330747","https://openalex.org/W3127348940","https://openalex.org/W4205778870","https://openalex.org/W4211083646","https://openalex.org/W6604498989","https://openalex.org/W6631362777","https://openalex.org/W6661582794","https://openalex.org/W6730678351"],"related_works":["https://openalex.org/W1509813908","https://openalex.org/W2031820693","https://openalex.org/W3024816962","https://openalex.org/W973023320","https://openalex.org/W1910172735","https://openalex.org/W2118307209","https://openalex.org/W2107364365","https://openalex.org/W2107688514","https://openalex.org/W2137288760","https://openalex.org/W3121710301"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,102],"approach":[4],"for":[5],"optimizing":[6],"a":[7,26,45,70,85,89],"Convolutional":[8],"BeamFormer":[9],"(CBF)":[10],"that":[11,31,87,111],"can":[12],"jointly":[13],"perform":[14],"denoising":[15],"(DN),":[16],"dereverberation":[17],"(DR),":[18],"and":[19,49,72,118,138],"source":[20,94],"separation":[21],"(SS).":[22],"First,":[23],"we":[24,58,83],"develop":[25,84],"blind":[27,117],"CBF":[28,71,99,128],"optimization":[29,55,100],"algorithm":[30],"requires":[32],"no":[33],"prior":[34],"information":[35],"on":[36],"the":[37,40,54,63,65,73,81,123,132],"sources":[38],"or":[39],"room":[41],"acoustics,":[42],"by":[43,101],"extending":[44],"conventional":[46,124],"joint":[47],"DR":[48],"SS":[50],"method.":[51],"For":[52],"making":[53],"computationally":[56],"tractable,":[57],"incorporate":[59],"two":[60],"techniques":[61],"into":[62],"approach:":[64],"Source-Wise":[66],"Factorization":[67],"(SW-Fact)":[68],"of":[69,131],"Independent":[74],"Vector":[75],"Extraction":[76],"(IVE).":[77],"To":[78],"further":[79],"improve":[80],"performance,":[82],"method":[86,114],"integrates":[88],"neural":[90],"network":[91],"(NN)":[92],"based":[93],"power":[95],"spectra":[96],"estimation":[97],"with":[98,115],"inverse-Gamma":[103],"prior.":[104],"Experiments":[105],"using":[106],"noisy":[107],"reverberant":[108],"mixtures":[109],"reveal":[110],"our":[112],"proposed":[113],"both":[116],"NN-guided":[119],"scenarios":[120],"greatly":[121],"outperforms":[122],"state-of-the-art":[125],"NN-supported":[126],"mask-based":[127],"in":[129,134],"terms":[130],"improvement":[133],"automatic":[135],"speech":[136],"recognition":[137],"signal":[139],"distortion":[140],"reduction":[141],"performance.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}