{"id":"https://openalex.org/W4403126470","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694042","title":"Joint Audio Source Localization and Separation with Distributed Microphone Arrays Based on Spatially-Regularized Multichannel NMF","display_name":"Joint Audio Source Localization and Separation with Distributed Microphone Arrays Based on Spatially-Regularized Multichannel NMF","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4403126470","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694042"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc61483.2024.10694042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-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/A5034515874","display_name":"Yoshiaki Sumura","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiaki Sumura","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023307571","display_name":"Diego Di Carlo","orcid":"https://orcid.org/0000-0002-4090-2872"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Diego Di Carlo","raw_affiliation_strings":["RIKEN,Center for Advanced Intelligence Project (AIP),Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN,Center for Advanced Intelligence Project (AIP),Tokyo,Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082272880","display_name":"Aditya Arie Nugraha","orcid":"https://orcid.org/0000-0001-5424-747X"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aditya Arie Nugraha","raw_affiliation_strings":["RIKEN,Center for Advanced Intelligence Project (AIP),Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN,Center for Advanced Intelligence Project (AIP),Tokyo,Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007353694","display_name":"Yoshiaki Bando","orcid":"https://orcid.org/0000-0002-3934-0745"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiaki Bando","raw_affiliation_strings":["National Institute for Advanced Industrial Science and Technology (AIST),Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute for Advanced Industrial Science and Technology (AIST),Tokyo,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Kyoto University,Graduate School of Engineering,Kyoto,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Engineering,Kyoto,Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1262,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77732256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"145","last_page":"149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9857000112533569,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9562000036239624,"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/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.7097578048706055},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6997389197349548},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6884440779685974},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6825995445251465},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6803829669952393},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.4645850956439972},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43780848383903503},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.22706538438796997},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11041444540023804},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0787690281867981},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07777118682861328}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.7097578048706055},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6997389197349548},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6884440779685974},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6825995445251465},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6803829669952393},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.4645850956439972},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43780848383903503},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.22706538438796997},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11041444540023804},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0787690281867981},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07777118682861328},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc61483.2024.10694042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","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":27,"referenced_works":["https://openalex.org/W1845880232","https://openalex.org/W1996355918","https://openalex.org/W2125937161","https://openalex.org/W2143027228","https://openalex.org/W2168273590","https://openalex.org/W2205284368","https://openalex.org/W2412956798","https://openalex.org/W2747805921","https://openalex.org/W2763188033","https://openalex.org/W2883322837","https://openalex.org/W2918296821","https://openalex.org/W2937284863","https://openalex.org/W2943237054","https://openalex.org/W2954049404","https://openalex.org/W2964208065","https://openalex.org/W2979850772","https://openalex.org/W2987410580","https://openalex.org/W3117396592","https://openalex.org/W3160845765","https://openalex.org/W3198425604","https://openalex.org/W3212886388","https://openalex.org/W4225316950","https://openalex.org/W4312805621","https://openalex.org/W4362653188","https://openalex.org/W4389315128","https://openalex.org/W6605586388","https://openalex.org/W6798679566"],"related_works":["https://openalex.org/W2351387116","https://openalex.org/W2361100278","https://openalex.org/W1658347130","https://openalex.org/W2547262076","https://openalex.org/W2398836525","https://openalex.org/W2563421448","https://openalex.org/W1509813908","https://openalex.org/W2774154397","https://openalex.org/W1565566036","https://openalex.org/W2921513691"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,22,35,83,88,107],"statistically":[4],"principled":[5],"method":[6,93,101],"that":[7],"simultaneously":[8],"localizes":[9],"and":[10,51,72,111,140,148],"separates":[11],"multiple":[12,16,55,59,103,151],"sound":[13],"sources":[14,60,152],"using":[15,128],"calibrated":[17],"microphone":[18,37,104,178],"arrays":[19,105,179],"distributed":[20],"in":[21,58],"room.":[23],"Given":[24],"the":[25,67,73,115,129,134,138,157,164,167],"extensive":[26],"research":[27],"on":[28,48,114],"direction":[29],"of":[30,87,121,137,150,166,180],"arrival":[31],"(DOA)":[32],"estimation":[33,170],"with":[34],"single":[36,108],"array,":[38],"for":[39,171],"3D":[40,135],"source":[41,91,130,139],"localization,":[42],"one":[43],"may":[44],"attempt":[45],"triangulation":[46],"based":[47],"DOAs":[49],"separately":[50],"egocentrically":[52],"estimated":[53,155],"by":[54,175],"arrays.":[56,141],"However,":[57],"scenarios,":[61],"this":[62],"cascading":[63],"approach":[64],"faces":[65],"both":[66],"inter-array":[68],"DOA":[69,131],"association":[70],"problem":[71],"error":[74],"accumulation":[75],"problem.":[76],"To":[77],"solve":[78],"these":[79],"problems,":[80],"we":[81],"propose":[82],"spatially":[84],"regularized":[85],"extension":[86],"versatile":[89],"blind":[90],"separation":[92],"called":[94],"multichannel":[95],"nonnegative":[96],"matrix":[97],"factorization":[98],"(MNMF).":[99],"Our":[100],"treats":[102],"as":[106],"big":[109],"array":[110],"puts":[112],"priors":[113,125],"frequency-wise":[116],"spatial":[117],"covariance":[118],"matrices":[119],"(SCMs)":[120],"each":[122],"source.":[123],"These":[124],"are":[126,153],"defined":[127],"computed":[132],"from":[133],"positions":[136,149],"The":[142],"power":[143],"spectral":[144],"densities":[145],"(PSDs),":[146],"SCMs,":[147],"jointly":[154],"under":[156],"unified":[158],"maximum-a-posteriori":[159],"(MAP)":[160],"principle.":[161],"We":[162],"show":[163],"effectiveness":[165],"joint":[168],"statistical":[169],"real":[172],"data":[173],"recorded":[174],"four":[176],"five-channel":[177],"Microsoft":[181],"Azure":[182],"Kinect.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}