{"id":"https://openalex.org/W2982840733","doi":"https://doi.org/10.23919/eusipco.2019.8903054","title":"Generalized Multichannel Variational Autoencoder for Underdetermined Source Separation","display_name":"Generalized Multichannel Variational Autoencoder for Underdetermined Source Separation","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2982840733","doi":"https://doi.org/10.23919/eusipco.2019.8903054","mag":"2982840733"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2019.8903054","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8903054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th European Signal Processing Conference (EUSIPCO)","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/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":["Nagoya University, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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/I4210105847","display_name":"NTT Basic Research Laboratories","ror":"https://ror.org/01m2pas06","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210105847"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Communication Science Laboratories, Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Atsugi, Japan","institution_ids":["https://openalex.org/I4210105847"]}]},{"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":["University of Tsukuba, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["Nagoya University, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101685454","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0003-0452-9844"},"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":["Nagoya University, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9990000128746033,"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":0.9990000128746033,"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/underdetermined-system","display_name":"Underdetermined system","score":0.9591032266616821},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8839706182479858},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.8064368963241577},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.781292200088501},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7805951833724976},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6795899868011475},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.6108729243278503},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.45225998759269714},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4278995394706726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4169083833694458},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4151252806186676},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4148257076740265},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3618132174015045},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3461032509803772},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.3136841654777527},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2920032739639282}],"concepts":[{"id":"https://openalex.org/C179690561","wikidata":"https://www.wikidata.org/wiki/Q4316110","display_name":"Underdetermined system","level":2,"score":0.9591032266616821},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8839706182479858},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8064368963241577},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.781292200088501},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7805951833724976},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6795899868011475},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.6108729243278503},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.45225998759269714},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4278995394706726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4169083833694458},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4151252806186676},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4148257076740265},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3618132174015045},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3461032509803772},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3136841654777527},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2920032739639282},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco.2019.8903054","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8903054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th European Signal Processing Conference (EUSIPCO)","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":31,"referenced_works":["https://openalex.org/W188967299","https://openalex.org/W1512388774","https://openalex.org/W1543386260","https://openalex.org/W1845880232","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/W2168273590","https://openalex.org/W2408744528","https://openalex.org/W2412956798","https://openalex.org/W2766672686","https://openalex.org/W2792498316","https://openalex.org/W2792765008","https://openalex.org/W2796495654","https://openalex.org/W2804271779","https://openalex.org/W2886577208","https://openalex.org/W2901552243","https://openalex.org/W2949416428","https://openalex.org/W2963035245","https://openalex.org/W2964121744","https://openalex.org/W6632571750","https://openalex.org/W6640963894","https://openalex.org/W6675944832","https://openalex.org/W6678799340","https://openalex.org/W6713966589","https://openalex.org/W6715525401","https://openalex.org/W6754172774"],"related_works":["https://openalex.org/W2095924515","https://openalex.org/W2383973401","https://openalex.org/W2351680970","https://openalex.org/W2030887432","https://openalex.org/W2551137307","https://openalex.org/W2206857820","https://openalex.org/W2361100278","https://openalex.org/W2098101267","https://openalex.org/W2113403277","https://openalex.org/W1598723711"],"abstract_inverted_index":{"This":[0,100,119],"paper":[1,120],"deals":[2],"with":[3,56,62,135],"a":[4,70,84],"multichannel":[5],"audio":[6],"source":[7,30,96,109,146],"separation":[8,110,147],"problem":[9],"under":[10,125],"underdetermined":[11,136,145],"conditions.":[12],"Multi-channel":[13],"Non-negative":[14],"Matrix":[15],"Factorization":[16],"(MNMF)":[17],"is":[18,47,88],"one":[19,45],"of":[20,41,91,117,149],"the":[21,26,63,74,92,114,162,170],"powerful":[22],"approaches,":[23],"which":[24],"adopts":[25],"NMF":[27,64,93],"concept":[28],"for":[29,38,54,95],"power":[31,97,116],"spectrogram":[32,98],"modeling.":[33,99],"It":[34],"works":[35],"reasonably":[36],"well":[37],"particular":[39],"types":[40],"sound":[42],"sources,":[43],"however,":[44],"limitation":[46],"that":[48,58,130,161],"it":[49,131],"can":[50,132],"fail":[51],"to":[52,104,113],"work":[53],"sources":[55,153],"spectrograms":[57],"do":[59],"not":[60],"comply":[61],"model.":[65],"To":[66],"address":[67],"this":[68],"limitation,":[69],"novel":[71],"technique":[72],"called":[73],"Multichannel":[75],"Variational":[76],"Autoencoder":[77],"(MVAE)":[78],"method":[79,140,165],"was":[80,141],"recently":[81],"proposed,":[82],"where":[83],"Conditional":[85],"VAE":[86],"(CVAE)":[87],"used":[89],"instead":[90],"model":[94],"approach":[101],"has":[102],"shown":[103],"perform":[105],"impressively":[106],"in":[107],"determined":[108,126],"tasks":[111],"thanks":[112],"representation":[115],"DNNs.":[118],"generalizes":[121],"MVAE":[122,164],"originally":[123],"formulated":[124],"mixing":[127],"conditions":[128],"so":[129],"also":[133],"deal":[134],"cases.":[137],"The":[138],"proposed":[139],"evaluated":[142],"on":[143],"an":[144],"task":[148],"separating":[150],"out":[151],"three":[152],"from":[154],"two":[155],"microphone":[156],"inputs.":[157],"Experimental":[158],"results":[159],"revealed":[160],"generalized":[163],"achieved":[166],"better":[167],"performance":[168],"than":[169],"conventional":[171],"MNMF":[172],"method.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}