{"id":"https://openalex.org/W3163912061","doi":"https://doi.org/10.1109/icassp39728.2021.9415121","title":"Neural Network-Based Virtual Microphone Estimator","display_name":"Neural Network-Based Virtual Microphone Estimator","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163912061","doi":"https://doi.org/10.1109/icassp39728.2021.9415121","mag":"3163912061"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9415121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415121","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":["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/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 corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT corporation","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 corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT corporation","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT corporation","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT corporation","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT corporation","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":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6114","last_page":"6118"},"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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":0.9966999888420105,"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/microphone","display_name":"Microphone","score":0.835966944694519},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7535048723220825},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6772720217704773},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6111152172088623},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6085733771324158},{"id":"https://openalex.org/keywords/vmebus","display_name":"VMEbus","score":0.4269472658634186},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41172122955322266},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39193448424339294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36297208070755005},{"id":"https://openalex.org/keywords/data-acquisition","display_name":"Data acquisition","score":0.1316244900226593},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06658804416656494},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.0631740391254425}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.835966944694519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7535048723220825},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6772720217704773},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6111152172088623},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6085733771324158},{"id":"https://openalex.org/C117180269","wikidata":"https://www.wikidata.org/wiki/Q1377238","display_name":"VMEbus","level":3,"score":0.4269472658634186},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41172122955322266},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39193448424339294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36297208070755005},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.1316244900226593},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06658804416656494},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0631740391254425},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9415121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415121","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1815076433","https://openalex.org/W1987906574","https://openalex.org/W2061074721","https://openalex.org/W2113638573","https://openalex.org/W2123649031","https://openalex.org/W2127851351","https://openalex.org/W2160815625","https://openalex.org/W2168729028","https://openalex.org/W2263133179","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2514741789","https://openalex.org/W2765306205","https://openalex.org/W2920956780","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W2987559325","https://openalex.org/W3015788098","https://openalex.org/W3099330747","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6632891567","https://openalex.org/W6638545294","https://openalex.org/W6712626118"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W2120442551","https://openalex.org/W1980506188","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2900122540","https://openalex.org/W2963983801","https://openalex.org/W3119734852","https://openalex.org/W2804363668"],"abstract_inverted_index":{"Developing":[0],"microphone":[1,32,64,71,148],"array":[2],"technologies":[3],"for":[4,130,152],"a":[5,60,92,157],"small":[6],"number":[7,30],"of":[8,16,26,31,84,104],"microphones":[9,107],"is":[10],"important":[11],"due":[12],"to":[13,21],"the":[14,29,75,80,85,102,105,112,128,137,142,161,165],"constraints":[15],"many":[17],"devices.":[18],"One":[19],"direction":[20],"address":[22],"this":[23,52],"situation":[24],"consists":[25],"virtually":[27],"augmenting":[28],"signals,":[33],"e.g.,":[34],"based":[35],"on":[36,124,136],"several":[37],"physical":[38,132],"model":[39],"assumptions.":[40,134],"However,":[41],"such":[42],"assumptions":[43],"are":[44],"not":[45],"necessarily":[46],"met":[47],"in":[48,74],"realistic":[49],"conditions.":[50],"In":[51],"paper,":[53],"as":[54],"an":[55],"alternative":[56],"approach,":[57],"we":[58],"propose":[59],"neural":[61,88],"network-based":[62],"virtual":[63,70,106,147],"estimator":[65],"(NN-VME).":[66],"The":[67],"NN-VME":[68,113,144,162],"estimates":[69],"signals":[72],"directly":[73,123],"time":[76],"domain,":[77],"by":[78],"utilizing":[79],"precise":[81],"estimation":[82,149],"capability":[83],"recent":[86],"time-domain":[87],"networks.":[89],"We":[90],"adopt":[91],"fully":[93],"supervised":[94],"learning":[95],"framework":[96],"that":[97,141,156],"uses":[98],"actual":[99],"observations":[100,120],"at":[101,108],"locations":[103],"training":[109],"time.":[110],"Consequently,":[111],"can":[114],"be":[115],"trained":[116],"using":[117],"only":[118],"multi-channel":[119],"and":[121,155,168],"thus":[122],"real":[125,153],"recordings,":[126],"avoiding":[127],"need":[129],"unrealistic":[131],"model-based":[133],"Experiments":[135],"CHiME-4":[138],"corpus":[139],"show":[140],"proposed":[143],"achieves":[145],"high":[146],"performance":[150],"even":[151],"recordings":[154],"beamformer":[158],"augmented":[159],"with":[160],"improves":[163],"both":[164],"speech":[166],"enhancement":[167],"recognition":[169],"performance.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}