{"id":"https://openalex.org/W4383428229","doi":"https://doi.org/10.1109/taslp.2023.3293044","title":"PoP-IDLMA: Product-of-Prior Independent Deeply Learned Matrix Analysis for Multichannel Music Source Separation","display_name":"PoP-IDLMA: Product-of-Prior Independent Deeply Learned Matrix Analysis for Multichannel Music Source Separation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4383428229","doi":"https://doi.org/10.1109/taslp.2023.3293044"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3293044","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3293044","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10174659.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10174659.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036067847","display_name":"Takuya Hasumi","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takuya Hasumi","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102941659","display_name":"Tomohiko Nakamura","orcid":"https://orcid.org/0000-0003-4385-7170"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiko Nakamura","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4385-7170","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051506797","display_name":"Norihiro Takamune","orcid":"https://orcid.org/0000-0002-8102-3110"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Norihiro Takamune","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-8102-3110","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0876-5617","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071479017","display_name":"Daichi Kitamura","orcid":"https://orcid.org/0000-0003-1117-7939"},"institutions":[{"id":"https://openalex.org/I4210160866","display_name":"National Institute of Technology, Kagawa College","ror":"https://ror.org/04xfwhf17","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210120810","https://openalex.org/I4210160866"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daichi Kitamura","raw_affiliation_strings":["National Institute of Technology, Kagawa College, Kagawa, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1117-7939","affiliations":[{"raw_affiliation_string":"National Institute of Technology, Kagawa College, Kagawa, Japan","institution_ids":["https://openalex.org/I4210160866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079059380","display_name":"Yu Takahashi","orcid":"https://orcid.org/0000-0002-9589-0645"},"institutions":[{"id":"https://openalex.org/I1295929820","display_name":"Yamaha (Japan)","ror":"https://ror.org/05s7fvh27","country_code":"JP","type":"company","lineage":["https://openalex.org/I1295929820"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yu Takahashi","raw_affiliation_strings":["Yamaha Corporation, Shizuoka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9589-0645","affiliations":[{"raw_affiliation_string":"Yamaha Corporation, Shizuoka, Japan","institution_ids":["https://openalex.org/I1295929820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021841017","display_name":"Kazunobu Kondo","orcid":"https://orcid.org/0000-0001-7428-696X"},"institutions":[{"id":"https://openalex.org/I1295929820","display_name":"Yamaha (Japan)","ror":"https://ror.org/05s7fvh27","country_code":"JP","type":"company","lineage":["https://openalex.org/I1295929820"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunobu Kondo","raw_affiliation_strings":["Yamaha Corporation, Shizuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yamaha Corporation, Shizuoka, Japan","institution_ids":["https://openalex.org/I1295929820"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5036067847"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.1514,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78402971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"2680","last_page":"2694"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9998000264167786,"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":0.9980000257492065,"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":0.8155378103256226},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7365596294403076},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.727195143699646},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6648340225219727},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5698234438896179},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5247804522514343},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.4767744839191437},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.46171948313713074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45596569776535034},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.45142027735710144},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.44042038917541504},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.43641960620880127},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42340028285980225},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4208027422428131},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.41983795166015625},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37250322103500366},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3429601788520813},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1746511161327362},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.1170215904712677},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09496802091598511},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08942702412605286}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8155378103256226},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7365596294403076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.727195143699646},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6648340225219727},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5698234438896179},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5247804522514343},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.4767744839191437},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.46171948313713074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45596569776535034},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.45142027735710144},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.44042038917541504},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.43641960620880127},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42340028285980225},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4208027422428131},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.41983795166015625},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37250322103500366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3429601788520813},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1746511161327362},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.1170215904712677},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09496802091598511},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08942702412605286},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3293044","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3293044","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10174659.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1109/taslp.2023.3293044","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3293044","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10174659.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1547730489","display_name":null,"funder_award_id":"JPJSBP120197203","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7893352204","display_name":null,"funder_award_id":"JP21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4383428229.pdf","grobid_xml":"https://content.openalex.org/works/W4383428229.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W30945556","https://openalex.org/W108815450","https://openalex.org/W1543386260","https://openalex.org/W1544694506","https://openalex.org/W1594771616","https://openalex.org/W1663973292","https://openalex.org/W1815076433","https://openalex.org/W1902027874","https://openalex.org/W1987133051","https://openalex.org/W2027884847","https://openalex.org/W2039844283","https://openalex.org/W2072548008","https://openalex.org/W2113990625","https://openalex.org/W2114461480","https://openalex.org/W2116064496","https://openalex.org/W2127851351","https://openalex.org/W2156387975","https://openalex.org/W2168273590","https://openalex.org/W2170768669","https://openalex.org/W2245569228","https://openalex.org/W2408744528","https://openalex.org/W2412956798","https://openalex.org/W2804917410","https://openalex.org/W2912626244","https://openalex.org/W2916985722","https://openalex.org/W2946521785","https://openalex.org/W2954049404","https://openalex.org/W2998251729","https://openalex.org/W3039928442","https://openalex.org/W3081267827","https://openalex.org/W3161538827","https://openalex.org/W3170134172","https://openalex.org/W6600284362","https://openalex.org/W6601250350","https://openalex.org/W6638545294","https://openalex.org/W6682889407","https://openalex.org/W6690610466"],"related_works":["https://openalex.org/W2098101267","https://openalex.org/W2081322759","https://openalex.org/W2576645943","https://openalex.org/W2339777604","https://openalex.org/W2615370628","https://openalex.org/W2804271779","https://openalex.org/W2570632195","https://openalex.org/W1984517456","https://openalex.org/W2321942335","https://openalex.org/W2058269967"],"abstract_inverted_index":{"Independent":[0],"deeply":[1],"learned":[2],"matrix":[3,44],"analysis":[4],"(IDLMA)":[5],"is":[6],"a":[7,32,92,119],"state-of-the-art":[8],"determined":[9],"audio":[10],"source":[11,39,80,88,97,114,142,182],"separation":[12,54],"method":[13],"based":[14],"on":[15,104,158],"pretrained":[16],"deep":[17],"neural":[18],"networks":[19],"(DNNs).":[20],"Owing":[21],"to":[22,49],"the":[23,53,61,67,71,84,96,105,108,112,123,128,133,140,159,162,168,171,176,181],"excellent":[24],"expression":[25,134],"power":[26,98,135,183],"of":[27,35,56,63,95,101,107,136,161,170],"DNNs,":[28],"IDLMA":[29,57,148],"can":[30,126],"handle":[31,127],"wider":[33],"range":[34],"sources":[36],"than":[37],"conventional":[38],"models":[40,81,89,125,143,178],"such":[41],"as":[42],"nonegative":[43],"factorization":[45],"(NMF).":[46],"However,":[47],"owing":[48],"its":[50],"supervised":[51],"nature,":[52],"performance":[55],"often":[58],"degrades":[59],"in":[60,185],"presence":[62],"timbral":[64,129],"mismatches":[65],"between":[66],"training":[68],"data":[69],"and":[70,86,151,174],"to-be-separated":[72],"data.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77,146],"propose":[78,147],"two":[79],"that":[82,175],"encompass":[83],"NMF-":[85],"DNN-based":[87],"by":[90],"constructing":[91],"prior":[93],"distribution":[94],"spectrogram":[99],"(product":[100],"priors:":[102],"PoP)":[103],"basis":[106,160],"product-of-expert":[109],"concept.":[110],"Since":[111],"NMF-based":[113],"model":[115],"works":[116],"well":[117],"for":[118],"fully":[120],"blind":[121],"situation,":[122],"proposed":[124,172,177],"mismatch":[130],"without":[131],"losing":[132],"DNNs.":[137],"By":[138],"introducing":[139],"PoP-based":[141],"into":[144],"IDLMA,":[145],"extensions":[149],"(PoP-IDLMAs)":[150],"derive":[152],"their":[153],"efficient":[154],"parameter":[155],"estimation":[156,184],"algorithms":[157],"majorization\u2013minimization":[163],"algorithm.":[164],"Experimental":[165],"results":[166],"demonstrated":[167],"effectiveness":[169],"PoP-IDLMAs":[173],"greatly":[179],"improve":[180],"frequency":[186],"bands":[187],"above":[188],"500":[189],"Hz.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}