{"id":"https://openalex.org/W2073146219","doi":"https://doi.org/10.1109/mlsp.2012.6349782","title":"Distributed microphone array processing for speech source separation with classifier fusion","display_name":"Distributed microphone array processing for speech source separation with classifier fusion","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W2073146219","doi":"https://doi.org/10.1109/mlsp.2012.6349782","mag":"2073146219"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2012.6349782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2012.6349782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Workshop on Machine Learning for Signal Processing","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/A5041575981","display_name":"Mehrez Souden","orcid":null},"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":"Mehrez Souden","raw_affiliation_strings":["NTT Communication Science Laboratories, Kyoto, Japan","[NTT Communication Science Laboratories, Kyoto, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"[NTT Communication Science Laboratories, Kyoto, 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, Kyoto, Japan","[NTT Communication Science Laboratories, Kyoto, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"[NTT Communication Science Laboratories, Kyoto, 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, Kyoto, Japan","[NTT Communication Science Laboratories, Kyoto, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"[NTT Communication Science Laboratories, Kyoto, Japan]","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","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, Kyoto, Japan","[NTT Communication Science Laboratories, Kyoto, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"[NTT Communication Science Laboratories, Kyoto, 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":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"1","last_page":"6"},"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":0.9986000061035156,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.7292065620422363},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7229869365692139},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.5931244492530823},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5840232968330383},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5784493088722229},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"Conditional independence","score":0.5564628839492798},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.5413988828659058},{"id":"https://openalex.org/keywords/array-processing","display_name":"Array processing","score":0.49250635504722595},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.48477381467819214},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.48385417461395264},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.46883100271224976},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.45812687277793884},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44718584418296814},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.44137436151504517},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.41947051882743835},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.30198127031326294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28993016481399536},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1930704116821289},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.1883562207221985},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1744706928730011},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09231150150299072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7292065620422363},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7229869365692139},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5931244492530823},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5840232968330383},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5784493088722229},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.5564628839492798},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.5413988828659058},{"id":"https://openalex.org/C2778545087","wikidata":"https://www.wikidata.org/wiki/Q4795883","display_name":"Array processing","level":4,"score":0.49250635504722595},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.48477381467819214},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.48385417461395264},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.46883100271224976},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.45812687277793884},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44718584418296814},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.44137436151504517},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.41947051882743835},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.30198127031326294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28993016481399536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1930704116821289},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.1883562207221985},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1744706928730011},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09231150150299072},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp.2012.6349782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2012.6349782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Workshop on Machine Learning for Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1987906574","https://openalex.org/W2021708956","https://openalex.org/W2031583051","https://openalex.org/W2037592772","https://openalex.org/W2059172134","https://openalex.org/W2071608040","https://openalex.org/W2104924323","https://openalex.org/W2110444924","https://openalex.org/W2114826795","https://openalex.org/W2117678320","https://openalex.org/W2120608389","https://openalex.org/W2127671620","https://openalex.org/W2127851351","https://openalex.org/W2129227482","https://openalex.org/W2158275940","https://openalex.org/W2165499073","https://openalex.org/W2166458192","https://openalex.org/W2169147844","https://openalex.org/W4246275837","https://openalex.org/W4295679937"],"related_works":["https://openalex.org/W1912396551","https://openalex.org/W4385692880","https://openalex.org/W2982120631","https://openalex.org/W2088740872","https://openalex.org/W2899781225","https://openalex.org/W2129566906","https://openalex.org/W2205284368","https://openalex.org/W2903040254","https://openalex.org/W2593303473","https://openalex.org/W4297695677"],"abstract_inverted_index":{"We":[0,113],"propose":[1],"a":[2,13],"new":[3],"approach":[4,19],"for":[5],"clustering":[6,164],"and":[7,88,108,158],"separating":[8],"competing":[9],"speech":[10,143],"signals":[11],"using":[12],"distributed":[14,35],"microphone":[15],"array":[16],"(DMA).":[17],"This":[18],"can":[20,137,159],"be":[21,66],"viewed":[22],"as":[23],"an":[24],"extension":[25],"of":[26,47,51,61,124,130,167],"expectation-maximization":[27],"(EM)-based":[28],"source":[29,169],"separation":[30,139,170],"to":[31,44,65],"DMAs.":[32],"To":[33],"achieve":[34,138],"processing,":[36],"we":[37,118,136],"assume":[38],"the":[39,48,58,71,79,93,99,150,155],"conditional":[40],"independence":[41],"(with":[42],"respect":[43],"sources'":[45,62],"activities)":[46],"normalized":[49],"recordings":[50],"different":[52],"nodes.":[53,69,91],"By":[54],"doing":[55],"so,":[56],"only":[57],"posterior":[59,83,133],"probabilities":[60,84,101],"activities":[63],"need":[64],"shared":[67,89],"between":[68,90],"Consequently,":[70],"EM":[72,127],"algorithm":[73],"is":[74],"formulated":[75],"such":[76],"that":[77,149],"at":[78],"expectation":[80],"step,":[81,95],"local":[82,111],"are":[85],"estimated":[86],"locally":[87],"In":[92],"maximization":[94],"every":[96],"node":[97],"fuses":[98],"received":[100],"via":[102],"either":[103],"product":[104],"or":[105],"sum":[106],"rules":[107],"estimates":[109],"its":[110],"parameters.":[112],"show":[114],"that,":[115],"even":[116],"if":[117],"make":[119],"binary":[120],"decisions":[121],"(presence/":[122],"absence":[123],"speech)":[125],"during":[126],"iterations":[128],"instead":[129],"transmitting":[131],"continuous":[132],"probability":[134],"values,":[135],"without":[140],"causing":[141],"significant":[142],"distortion.":[144],"Our":[145],"preliminary":[146],"investigations":[147],"demonstrate":[148],"proposed":[151],"processing":[152],"technique":[153],"approaches":[154],"centralized":[156],"solution":[157],"outperform":[160],"Oracle":[161],"best":[162],"node-wise":[163],"in":[165],"terms":[166],"objective":[168],"metrics.":[171]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}