{"id":"https://openalex.org/W3015661721","doi":"https://doi.org/10.1109/icassp40776.2020.9053343","title":"DNN-supported Mask-based Convolutional Beamforming for Simultaneous Denoising, Dereverberation, and Source Separation","display_name":"DNN-supported Mask-based Convolutional Beamforming for Simultaneous Denoising, Dereverberation, and Source Separation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015661721","doi":"https://doi.org/10.1109/icassp40776.2020.9053343","mag":"3015661721"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/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, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018006253","display_name":"Riki Takahashi","orcid":"https://orcid.org/0009-0002-2930-0122"},"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":"Riki Takahashi","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"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":"Tsubasa Ochiai","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, 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 Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, 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 Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 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, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, 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 Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, 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":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6399","last_page":"6403"},"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":0.9965999722480774,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7439730167388916},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7290205955505371},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6074339747428894},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5968198776245117},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5966801047325134},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5830978751182556},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5800851583480835},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.5317358374595642},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5017960071563721},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4542262852191925},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45028218626976013},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4501049220561981},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32759565114974976},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.11721619963645935},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11387178301811218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7439730167388916},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7290205955505371},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6074339747428894},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5968198776245117},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5966801047325134},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5830978751182556},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5800851583480835},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.5317358374595642},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5017960071563721},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4542262852191925},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45028218626976013},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4501049220561981},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32759565114974976},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.11721619963645935},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11387178301811218},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":34,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1503775994","https://openalex.org/W1524333225","https://openalex.org/W1956364622","https://openalex.org/W1983812858","https://openalex.org/W2031583051","https://openalex.org/W2060108923","https://openalex.org/W2130722890","https://openalex.org/W2164502538","https://openalex.org/W2242685705","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2591810467","https://openalex.org/W2640112133","https://openalex.org/W2702006285","https://openalex.org/W2714509385","https://openalex.org/W2734774145","https://openalex.org/W2750380122","https://openalex.org/W2772837889","https://openalex.org/W2803322398","https://openalex.org/W2892163332","https://openalex.org/W2903083210","https://openalex.org/W2905402910","https://openalex.org/W2952218014","https://openalex.org/W2952752702","https://openalex.org/W2966098955","https://openalex.org/W2972492143","https://openalex.org/W2972693890","https://openalex.org/W2989287578","https://openalex.org/W3015306655","https://openalex.org/W3098052090","https://openalex.org/W3099330747","https://openalex.org/W6631362777","https://openalex.org/W6769366077"],"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/W2539388437","https://openalex.org/W2107688514","https://openalex.org/W2137288760"],"abstract_inverted_index":{"In":[0],"this":[1,68],"article,":[2],"we":[3,70],"investigate":[4],"an":[5],"integrated":[6],"mask-based":[7,26,63,79],"convolutional":[8,120],"beamforming":[9,80],"method":[10,73],"for":[11,23,39,78,131],"performing":[12],"simultaneous":[13],"denoising,":[14],"dereverberation,":[15],"and":[16,32,38,55,113],"source":[17,27,42,64],"separation.":[18,65],"Conventionally,":[19],"it":[20],"is":[21],"difficult":[22],"neural":[24],"network-supported":[25],"separation":[28,43],"to":[29,44,74],"perform":[30],"denoising":[31],"dereverberation":[33],"at":[34],"the":[35,47,51,60],"same":[36],"time":[37],"spatial":[40,110],"clustering-based":[41],"reliably":[45],"solve":[46],"permutation":[48],"problem":[49],"in":[50,137],"presence":[52],"of":[53,62],"noise":[54],"reverberation.":[56],"This":[57],"greatly":[58],"limits":[59],"application":[61],"To":[66],"address":[67],"issue,":[69],"propose":[71],"a":[72,82,99],"integrate":[75],"state-of-the-art":[76],"techniques":[77,87],"into":[81],"single":[83],"optimization":[84],"framework.":[85],"These":[86],"include":[88],"frequency-domain":[89],"Convolutional":[90],"Neural":[91],"Network":[92],"based":[93,109],"utterance-level":[94],"Permutation":[95],"Invariant":[96],"Training":[97],"with":[98],"large":[100],"receptive":[101],"field":[102],"(CNN-uPIT),":[103],"noisy":[104,138],"Complex":[105],"Gaussian":[106],"Mixture":[107],"Model":[108],"clustering":[111],"(noisyCGMM),":[112],"Weighted":[114],"Power":[115],"minimization":[116],"Distortionless":[117],"response":[118],"(WPD)":[119],"beamforming.":[121],"Our":[122],"experiments":[123],"show":[124],"that":[125],"all":[126],"these":[127],"components":[128],"are":[129],"essential":[130],"accurately":[132],"estimating":[133],"desired":[134],"speech":[135],"signals":[136],"reverberant":[139],"multisource":[140],"environments.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}