{"id":"https://openalex.org/W2785864403","doi":"https://doi.org/10.1109/asru.2017.8268916","title":"Improving separation of overlapped speech for meeting conversations using uncalibrated microphone array","display_name":"Improving separation of overlapped speech for meeting conversations using uncalibrated microphone array","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2785864403","doi":"https://doi.org/10.1109/asru.2017.8268916","mag":"2785864403"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268916","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5049329632","display_name":"Keisuke Nakamura","orcid":"https://orcid.org/0000-0002-4979-2083"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Nakamura","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd., Saitama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd., Saitama, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052470310","display_name":"Randy G\u00f3mez","orcid":"https://orcid.org/0000-0002-3191-6818"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Randy Gomez","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd., Saitama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd., Saitama, Japan","institution_ids":["https://openalex.org/I1283473643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1283473643"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"55","last_page":"62"},"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":0.9983999729156494,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9952999949455261,"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/multilateration","display_name":"Multilateration","score":0.7871457934379578},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.7249858975410461},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.7005319595336914},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6867097020149231},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6638649702072144},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6168064475059509},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.5919446349143982},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5882106423377991},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5648344159126282},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5605733394622803},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4307302236557007},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4303815960884094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.346630722284317},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2712935507297516},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10732144117355347},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.08746826648712158},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.06318643689155579}],"concepts":[{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.7871457934379578},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.7249858975410461},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.7005319595336914},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6867097020149231},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6638649702072144},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6168064475059509},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.5919446349143982},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5882106423377991},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5648344159126282},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5605733394622803},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4307302236557007},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4303815960884094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.346630722284317},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2712935507297516},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10732144117355347},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.08746826648712158},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.06318643689155579},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8268916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268916","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"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":42,"referenced_works":["https://openalex.org/W7575313","https://openalex.org/W33176171","https://openalex.org/W182689536","https://openalex.org/W603591469","https://openalex.org/W1502984613","https://openalex.org/W1565072422","https://openalex.org/W1965279578","https://openalex.org/W1992106273","https://openalex.org/W2025344720","https://openalex.org/W2039206676","https://openalex.org/W2046317813","https://openalex.org/W2060108923","https://openalex.org/W2078385108","https://openalex.org/W2081074144","https://openalex.org/W2101169486","https://openalex.org/W2113638573","https://openalex.org/W2114970513","https://openalex.org/W2126693545","https://openalex.org/W2127851351","https://openalex.org/W2136745572","https://openalex.org/W2138838039","https://openalex.org/W2145303093","https://openalex.org/W2148613904","https://openalex.org/W2152321507","https://openalex.org/W2153842971","https://openalex.org/W2157850507","https://openalex.org/W2161270956","https://openalex.org/W2161947961","https://openalex.org/W2165232124","https://openalex.org/W2170768669","https://openalex.org/W2406347618","https://openalex.org/W2541658920","https://openalex.org/W2568308529","https://openalex.org/W2575105060","https://openalex.org/W2591682631","https://openalex.org/W2767017816","https://openalex.org/W6600315864","https://openalex.org/W6618327443","https://openalex.org/W6670935036","https://openalex.org/W6680459256","https://openalex.org/W6682935373","https://openalex.org/W6714003466"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2188292175","https://openalex.org/W2385053527","https://openalex.org/W1983991597","https://openalex.org/W4386900535","https://openalex.org/W2769861442","https://openalex.org/W2120442551","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,44,92],"propose":[4],"a":[5,141],"novel":[6],"approach":[7],"of":[8,40,48,59,100,104],"sound":[9],"source":[10],"separation":[11,123,151],"for":[12,29],"meeting":[13,143],"conversations":[14],"even":[15],"when":[16],"using":[17,83,112],"an":[18],"uncalibrated":[19],"microphone":[20],"array.":[21],"Our":[22],"method":[23],"can":[24],"blindly":[25,89,113,147],"estimate":[26,45],"three":[27],"parameters":[28,149],"separation,":[30],"namely":[31],"Steering":[32],"Vectors":[33],"(SVs),":[34],"speaker":[35,72],"indices,":[36],"and":[37,50,63,74,126,130,136,152],"activity":[38,75],"periods":[39,76],"each":[41],"speaker.":[42],"First,":[43],"the":[46,60,105,146],"number":[47],"speakers":[49],"SVs":[51],"by":[52,79],"clustering":[53],"Time":[54],"Delay":[55],"Of":[56],"Arrival":[57],"(TDOA)":[58],"observed":[61],"signal":[62],"selecting":[64],"major":[65],"clusters":[66],"to":[67,155],"compute":[68],"TDOA-based":[69],"SVs.":[70],"Then,":[71],"indices":[73],"are":[77],"estimated":[78,84,114,148],"thresholding":[80],"spatial":[81],"spectrum":[82],"SVs,":[85],"whose":[86],"threshold":[87],"is":[88],"obtained.":[90],"Finally,":[91],"separate":[93],"overlapped":[94],"speeches/noise":[95],"based":[96],"on":[97],"dynamic":[98],"design":[99],"noise":[101],"correlation":[102],"matrices":[103],"minimum":[106],"variance":[107],"distortionless":[108],"response":[109],"(MVDR)":[110],"beamformer":[111],"parameters.":[115,158],"The":[116],"proposed":[117],"algorithm":[118],"was":[119],"evaluated":[120],"in":[121,133,140],"both":[122,134],"objective":[124],"measure":[125],"recognition":[127,153],"correct":[128],"rate":[129],"showed":[131],"improvements":[132],"single":[135],"simultaneous":[137],"speech":[138],"scenarios":[139],"reverberant":[142],"room.":[144],"Moreover,":[145],"improved":[150],"compared":[154],"geometrically":[156],"obtained":[157]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}