{"id":"https://openalex.org/W2989942677","doi":"https://doi.org/10.1109/access.2019.2954120","title":"Underdetermined Source Separation Based on Generalized Multichannel Variational Autoencoder","display_name":"Underdetermined Source Separation Based on Generalized Multichannel Variational Autoencoder","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2989942677","doi":"https://doi.org/10.1109/access.2019.2954120","mag":"2989942677"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2954120","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2954120","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08906095.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08906095.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101792863","display_name":"Shogo Seki","orcid":"https://orcid.org/0000-0001-8284-188X"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shogo Seki","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8284-188X","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"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":"Hirokazu Kameoka","raw_affiliation_strings":["Nippon Telegraph and Telephone Corporation, Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone Corporation, Atsugi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361230","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-7163-6263"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":["Institutes of Innovation for Future Society, Nagoya University, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institutes of Innovation for Future Society, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.9448,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92105428,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"7","issue":null,"first_page":"168104","last_page":"168115"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9997000098228455,"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/underdetermined-system","display_name":"Underdetermined system","score":0.9685809016227722},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9041961431503296},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.7957140803337097},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7698630094528198},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7279797792434692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6630123257637024},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.6309589743614197},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5214628577232361},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.470140278339386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4048900008201599},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39540979266166687},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38974523544311523},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34111207723617554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3314322233200073}],"concepts":[{"id":"https://openalex.org/C179690561","wikidata":"https://www.wikidata.org/wiki/Q4316110","display_name":"Underdetermined system","level":2,"score":0.9685809016227722},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9041961431503296},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.7957140803337097},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7698630094528198},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7279797792434692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6630123257637024},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.6309589743614197},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5214628577232361},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.470140278339386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4048900008201599},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39540979266166687},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38974523544311523},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34111207723617554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3314322233200073},{"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/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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2954120","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2954120","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08906095.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:87d3296b7d2d414e895f24fbbe506e2d","is_oa":true,"landing_page_url":"https://doaj.org/article/87d3296b7d2d414e895f24fbbe506e2d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 168104-168115 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2954120","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2954120","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08906095.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1949028426","display_name":"\u4eba\u9593\u306e\u8074\u899a\u7279\u6027\u3092\u8003\u616e\u3057\u305f\u6b8b\u97ff\u30fb\u96d1\u97f3\u74b0\u5883\u4e0b\u306b\u304a\u3051\u308b\u97f3\u58f0\u4fe1\u53f7\u51e6\u7406\u306e\u7814\u7a76","funder_award_id":"18J20059","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5076414432","display_name":null,"funder_award_id":"JP17H01763","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6466568207","display_name":"Development of fundamental technology for speech and sound event processing based on complementary use of air- and body-conducted sound signals","funder_award_id":"17H01763","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W188967299","https://openalex.org/W1512388774","https://openalex.org/W1522301498","https://openalex.org/W1543386260","https://openalex.org/W1548802052","https://openalex.org/W1845880232","https://openalex.org/W1887941968","https://openalex.org/W1959608418","https://openalex.org/W2039844283","https://openalex.org/W2072548008","https://openalex.org/W2104298926","https://openalex.org/W2108501770","https://openalex.org/W2113990625","https://openalex.org/W2127851351","https://openalex.org/W2139302694","https://openalex.org/W2149414429","https://openalex.org/W2168273590","https://openalex.org/W2408744528","https://openalex.org/W2412956798","https://openalex.org/W2792498316","https://openalex.org/W2792765008","https://openalex.org/W2804271779","https://openalex.org/W2886577208","https://openalex.org/W2894192904","https://openalex.org/W2901552243","https://openalex.org/W2922004249","https://openalex.org/W2963035245","https://openalex.org/W2963375116","https://openalex.org/W2982840733","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6675944832","https://openalex.org/W6754172774","https://openalex.org/W6755236810"],"related_works":["https://openalex.org/W2383973401","https://openalex.org/W2034312940","https://openalex.org/W2351680970","https://openalex.org/W2095924515","https://openalex.org/W2551137307","https://openalex.org/W2030887432","https://openalex.org/W2900617041","https://openalex.org/W2361100278","https://openalex.org/W2098101267","https://openalex.org/W2113403277"],"abstract_inverted_index":{"This":[0,47,136],"paper":[1,167],"deals":[2],"with":[3,91,97,188],"a":[4,19,44,58,120,169],"multichannel":[5,111],"audio":[6,24],"source":[7,25,133,143,202],"separation":[8,144,203],"problem":[9],"under":[10,65,162],"underdetermined":[11,23,189,201],"conditions.":[12,67],"Multichannel":[13],"non-negative":[14],"matrix":[15,55],"factorization":[16],"(MNMF)":[17],"is":[18,49,82,124],"powerful":[20],"method":[21,115,159,194,210],"for":[22,74,89,131],"separation,":[26],"which":[27],"adopts":[28],"the":[29,36,40,62,98,110,128,148,156,176,195,208],"NMF":[30,99,129],"concept":[31,48],"to":[32,87,147],"model":[33,130],"and":[34,180,204],"estimate":[35],"power":[37,134,150],"spectrograms":[38,92],"of":[39,61,77,107,127,151,172,178],"sound":[41,78],"sources":[42,90],"in":[43,52,141],"mixture":[45],"signal.":[46],"also":[50,186],"used":[51,125],"independent":[53],"low-rank":[54],"analysis":[56],"(ILRMA),":[57],"special":[59],"class":[60],"MNMF":[63,179],"formulated":[64,161],"determined":[66,142,163],"While":[68,155],"these":[69],"methods":[70],"work":[71,88],"reasonably":[72],"well":[73],"particular":[75],"types":[76],"sources,":[79],"one":[80],"limitation":[81],"that":[83,93,183],"they":[84],"can":[85,185],"fail":[86],"do":[94],"not":[95],"comply":[96],"model.":[100],"To":[101],"address":[102],"this":[103,166,193],"limitation,":[104],"an":[105],"extension":[106],"ILRMA":[108],"called":[109],"variational":[112],"autoencoder":[113],"(MVAE)":[114],"was":[116,160],"recently":[117],"proposed,":[118],"where":[119],"conditional":[121],"VAE":[122],"(CVAE)":[123],"instead":[126],"expressing":[132],"spectrograms.":[135],"approach":[137],"has":[138],"performed":[139,211],"impressively":[140],"tasks":[145],"thanks":[146],"representation":[149],"deep":[152],"neural":[153],"networks.":[154],"original":[157],"MVAE":[158,181,197],"mixing":[164],"conditions,":[165],"proposes":[168],"generalized":[170,196],"version":[171],"it":[173,184],"by":[174],"combining":[175],"ideas":[177],"so":[182],"deal":[187],"cases.":[190],"We":[191],"call":[192],"(GMVAE)":[198],"method.":[199],"In":[200],"speech":[205],"enhancement":[206],"experiments,":[207],"proposed":[209],"better":[212],"than":[213],"baseline":[214],"methods.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5}],"updated_date":"2026-05-19T21:40:30.786675","created_date":"2025-10-10T00:00:00"}