{"id":"https://openalex.org/W4392910826","doi":"https://doi.org/10.1109/icassp48485.2024.10446139","title":"Neural Network-Based Virtual Microphone Estimation with Virtual Microphone and Beamformer-Level Multi-Task Loss","display_name":"Neural Network-Based Virtual Microphone Estimation with Virtual Microphone and Beamformer-Level Multi-Task Loss","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910826","doi":"https://doi.org/10.1109/icassp48485.2024.10446139"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5089152590","display_name":"Hanako Segawa","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hanako Segawa","raw_affiliation_strings":["University of Tsukuba,Japan","University of Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"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 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/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,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/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/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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083303913","display_name":"Takeshi Yamada","orcid":"https://orcid.org/0000-0002-1436-7482"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Yamada","raw_affiliation_strings":["University of Tsukuba,Japan","University of Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075702573","display_name":"Shoji Makino","orcid":"https://orcid.org/0000-0003-1934-640X"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]},{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoji Makino","raw_affiliation_strings":["University of Tsukuba,Japan","Waseda University, Japan","University of Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11021","last_page":"11025"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9302999973297119,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9282000064849854,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/microphone","display_name":"Microphone","score":0.7893660068511963},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7233046889305115},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6494331359863281},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5867577791213989},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5688841342926025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4133811593055725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27760207653045654},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1315978765487671},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07284572720527649}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7893660068511963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7233046889305115},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6494331359863281},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5867577791213989},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5688841342926025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4133811593055725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27760207653045654},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1315978765487671},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07284572720527649},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/W650496799","https://openalex.org/W811578723","https://openalex.org/W1987906574","https://openalex.org/W2024490156","https://openalex.org/W2060108923","https://openalex.org/W2061074721","https://openalex.org/W2117678320","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/W2517616541","https://openalex.org/W2734774145","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2987559325","https://openalex.org/W3015788098","https://openalex.org/W3099330747","https://openalex.org/W3163912061","https://openalex.org/W4224920397","https://openalex.org/W4239943352","https://openalex.org/W4249052411","https://openalex.org/W4293363567","https://openalex.org/W4297841603","https://openalex.org/W4312069010","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2149163000","https://openalex.org/W2041060376","https://openalex.org/W2963983801"],"abstract_inverted_index":{"Array":[0],"processing":[1,65],"performance":[2],"depends":[3],"on":[4,87,131],"the":[5,19,80,88,105,127],"number":[6,20],"of":[7,21,107],"microphones":[8,151],"available.":[9],"Virtual":[10],"microphone":[11,22,42],"estimation":[12],"(VME)":[13],"has":[14],"been":[15],"proposed":[16,128],"to":[17,36,74,147,156],"increase":[18],"signals":[23,95],"artificially.":[24],"Neural":[25],"network-based":[26],"VME":[27],"(NN-VME)":[28],"trains":[29],"an":[30],"NN":[31],"with":[32],"a":[33,38,41,62,76,85,113,140,158],"VM-level":[34,121],"loss":[35,86,115],"predict":[37],"signal":[39],"at":[40,51],"location":[43],"that":[44,118,137],"is":[45,73],"available":[46],"during":[47],"training":[48,55,77],"but":[49,99],"not":[50,58,100],"inference.":[52],"However,":[53],"this":[54,110],"objective":[56,78],"may":[57,93],"be":[59],"optimal":[60,96],"for":[61,97,116],"specific":[63],"array":[64],"back-end,":[66,82],"such":[67,83],"as":[68,84],"beamforming.":[69],"An":[70],"alternative":[71],"approach":[72,92],"use":[75],"considering":[79],"array-processing":[81],"beamformer":[89],"output.":[90],"This":[91],"generate":[94],"beamforming":[98],"physically":[101],"grounded.":[102],"To":[103],"combine":[104],"advantages":[106],"both":[108,120],"approaches,":[109],"paper":[111],"proposes":[112],"multi-task":[114,129],"NN-VME":[117,130,160],"combines":[119],"and":[122,135,152],"beamformer-level":[123],"losses.":[124],"We":[125],"evaluate":[126],"multi-talker":[132],"underdetermined":[133],"conditions":[134],"show":[136],"it":[138],"achieves":[139],"33.1":[141],"%":[142,154],"relative":[143],"WER":[144],"improvement":[145],"compared":[146,155],"using":[148,157],"only":[149],"real":[150],"10.8":[153],"prior":[159],"approach.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
