{"id":"https://openalex.org/W2049919499","doi":"https://doi.org/10.1109/taslp.2013.2292308","title":"Location Feature Integration for Clustering-Based Speech Separation in Distributed Microphone Arrays","display_name":"Location Feature Integration for Clustering-Based Speech Separation in Distributed Microphone Arrays","publication_year":2014,"publication_date":"2014-01-06","ids":{"openalex":"https://openalex.org/W2049919499","doi":"https://doi.org/10.1109/taslp.2013.2292308","mag":"2049919499"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2013.2292308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2013.2292308","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","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/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehrez Souden","raw_affiliation_strings":["Sch. of Electr. & Comput. Eng.,, Georgia Inst. of Technol., Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sch. of Electr. & Comput. Eng.,, Georgia Inst. of Technol., Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"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]"],"raw_orcid":null,"affiliations":[{"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]"],"raw_orcid":null,"affiliations":[{"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]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[NTT Communication Science Laboratories, Kyoto, Japan]","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6068,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.90281748,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"22","issue":"2","first_page":"354","last_page":"367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9965000152587891,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7818113565444946},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7561538219451904},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6024012565612793},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6018650531768799},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5553438663482666},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5203332901000977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4979074001312256},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33912432193756104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27356380224227905},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10023936629295349},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07226663827896118}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7818113565444946},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7561538219451904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6024012565612793},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6018650531768799},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5553438663482666},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5203332901000977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4979074001312256},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33912432193756104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27356380224227905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10023936629295349},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07226663827896118},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/taslp.2013.2292308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2013.2292308","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W190008395","https://openalex.org/W1500379785","https://openalex.org/W1515932869","https://openalex.org/W1976805820","https://openalex.org/W1981446207","https://openalex.org/W1987906574","https://openalex.org/W1991082011","https://openalex.org/W2003321974","https://openalex.org/W2020125737","https://openalex.org/W2031583051","https://openalex.org/W2043216213","https://openalex.org/W2055012008","https://openalex.org/W2059172134","https://openalex.org/W2061074721","https://openalex.org/W2071608040","https://openalex.org/W2073146219","https://openalex.org/W2073856445","https://openalex.org/W2104924323","https://openalex.org/W2106510159","https://openalex.org/W2107992675","https://openalex.org/W2110444924","https://openalex.org/W2114826795","https://openalex.org/W2117678320","https://openalex.org/W2120608389","https://openalex.org/W2127851351","https://openalex.org/W2131552695","https://openalex.org/W2146917306","https://openalex.org/W2147665979","https://openalex.org/W2152594362","https://openalex.org/W2156703461","https://openalex.org/W2158275940","https://openalex.org/W2158307424","https://openalex.org/W2165499073","https://openalex.org/W2166458192","https://openalex.org/W2171396090","https://openalex.org/W2950424803","https://openalex.org/W3008609509","https://openalex.org/W4246275837","https://openalex.org/W4249052411","https://openalex.org/W6655352274","https://openalex.org/W6683212022"],"related_works":["https://openalex.org/W2161947961","https://openalex.org/W2116623987","https://openalex.org/W1488173215","https://openalex.org/W2165869870","https://openalex.org/W1491017269","https://openalex.org/W2053655562","https://openalex.org/W1977167953","https://openalex.org/W2155276444","https://openalex.org/W1607399658","https://openalex.org/W2149163000"],"abstract_inverted_index":{"In":[0],"distributed":[1,54],"microphone":[2],"arrays":[3],"(DMAs)":[4],"the":[5,13,20,27,37,40,45,48,65,86,91,97,105,112,119,123,131,154,165,176],"source":[6],"location":[7,146],"information":[8,24,121],"can":[9],"be":[10],"defined":[11],"at":[12,96],"intra":[14],"and":[15,64,78,110,128,140,156],"inter-node":[16,98,145,157],"levels.":[17],"Indeed,":[18],"while":[19,95],"first":[21],"type":[22],"of":[23,29,67,74,153,178],"results":[25,171],"from":[26],"diversity":[28],"acoustic":[30,49],"channels":[31,50],"recorded":[32],"by":[33,52],"microphones":[34],"embedded":[35],"in":[36,61],"same":[38],"node,":[39],"second":[41],"is":[42,70],"attributed":[43],"to":[44,71,76,142,160,174],"differences":[46,108,114],"between":[47,115],"observed":[51],"spatially":[53],"nodes.":[55,116],"Both":[56],"cues":[57],"are":[58,172],"very":[59],"useful":[60],"DMA":[62],"processing,":[63],"aim":[66],"this":[68],"paper":[69],"utilize":[72],"both":[73],"them":[75],"cluster":[77,161],"separate":[79],"multiple":[80],"competing":[81],"speech":[82,162],"signals.":[83],"To":[84],"capture":[85],"intra-node":[87,120,155],"information,":[88],"we":[89,100,149],"employ":[90],"normalized":[92],"recording":[93],"vector,":[94],"level,":[99],"consider":[101],"different":[102,144],"features":[103],"including":[104],"energy":[106],"level":[107],"with":[109],"without":[111],"phase":[113],"We":[117],"model":[118,126,134,138,143],"using":[122,130,164],"Watson":[124],"mixture":[125,133,137],"(WMM),":[127],"propose":[129,150],"Gamma":[132],"(GaMM),":[135],"Dirichlet":[136],"(DMM),":[139],"WMM":[141],"features.":[147],"Furthermore,":[148],"several":[151],"integrations":[152],"feature":[158],"contributions":[159],"recordings":[163],"expectation":[166],"maximization":[167],"algorithm.":[168],"Finally,":[169],"simulation":[170],"provided":[173],"demonstrate":[175],"performance":[177],"all":[179],"ensuing":[180],"methods.":[181]},"counts_by_year":[{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}