{"id":"https://openalex.org/W4310872040","doi":"https://doi.org/10.1109/taslp.2022.3214763","title":"FastMVAE2: On Improving and Accelerating the Fast Variational Autoencoder-Based Source Separation Algorithm for Determined Mixtures","display_name":"FastMVAE2: On Improving and Accelerating the Fast Variational Autoencoder-Based Source Separation Algorithm for Determined Mixtures","publication_year":2022,"publication_date":"2022-10-14","ids":{"openalex":"https://openalex.org/W4310872040","doi":"https://doi.org/10.1109/taslp.2022.3214763"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3214763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3214763","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/A5061981123","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-3121-7857"},"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"]},{"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":true,"raw_author_name":"Li Li","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Atsugi-shi, Japan","Nagoya University, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Atsugi-shi, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"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/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":["NTT Communication Science Laboratories, NTT Corporation, Atsugi-shi, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Atsugi-shi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075702573","display_name":"Shoji Makino","orcid":"https://orcid.org/0000-0003-1934-640X"},"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"]},{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoji Makino","raw_affiliation_strings":["Waseda University, Kitakyushu, Japan","University of Tsukuba, Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Kitakyushu, Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061981123"],"corresponding_institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":1.6355,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.83670738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"96","last_page":"110"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.9980999827384949,"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/autoencoder","display_name":"Autoencoder","score":0.7845891118049622},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7035263776779175},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6971272826194763},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6068780422210693},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.6045662760734558},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5900469422340393},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5614111423492432},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.54400235414505},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.45428040623664856},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.44445762038230896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44197148084640503},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42202234268188477},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3998562693595886},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17295467853546143},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.10771670937538147}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7845891118049622},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7035263776779175},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6971272826194763},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6068780422210693},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.6045662760734558},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5900469422340393},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5614111423492432},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.54400235414505},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.45428040623664856},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.44445762038230896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44197148084640503},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42202234268188477},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3998562693595886},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17295467853546143},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.10771670937538147},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3214763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3214763","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":100,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W613054787","https://openalex.org/W1512388774","https://openalex.org/W1522301498","https://openalex.org/W1543386260","https://openalex.org/W1552314771","https://openalex.org/W1572099565","https://openalex.org/W1821462560","https://openalex.org/W1836465849","https://openalex.org/W1845880232","https://openalex.org/W1887941968","https://openalex.org/W2014768838","https://openalex.org/W2058341666","https://openalex.org/W2062572859","https://openalex.org/W2067295501","https://openalex.org/W2072548008","https://openalex.org/W2086286498","https://openalex.org/W2095705004","https://openalex.org/W2096855653","https://openalex.org/W2108501770","https://openalex.org/W2113990625","https://openalex.org/W2116064496","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2135029798","https://openalex.org/W2139302694","https://openalex.org/W2144513243","https://openalex.org/W2165698076","https://openalex.org/W2168273590","https://openalex.org/W2188365844","https://openalex.org/W2221409856","https://openalex.org/W2408744528","https://openalex.org/W2412956798","https://openalex.org/W2460742184","https://openalex.org/W2548228487","https://openalex.org/W2567070169","https://openalex.org/W2734774145","https://openalex.org/W2750446090","https://openalex.org/W2766672686","https://openalex.org/W2792498316","https://openalex.org/W2800675406","https://openalex.org/W2808718747","https://openalex.org/W2883322837","https://openalex.org/W2889341949","https://openalex.org/W2892163332","https://openalex.org/W2894785362","https://openalex.org/W2901552243","https://openalex.org/W2911579794","https://openalex.org/W2922004249","https://openalex.org/W2936446744","https://openalex.org/W2946555236","https://openalex.org/W2952218014","https://openalex.org/W2952350176","https://openalex.org/W2954049404","https://openalex.org/W2954996726","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2963035245","https://openalex.org/W2963090522","https://openalex.org/W2963226019","https://openalex.org/W2963375116","https://openalex.org/W2963969588","https://openalex.org/W2968723745","https://openalex.org/W2972460025","https://openalex.org/W2979850772","https://openalex.org/W2989942677","https://openalex.org/W3015788098","https://openalex.org/W3035268204","https://openalex.org/W3094316140","https://openalex.org/W3096831136","https://openalex.org/W3099330747","https://openalex.org/W3106955634","https://openalex.org/W3117310166","https://openalex.org/W3141797743","https://openalex.org/W3151851237","https://openalex.org/W3163652268","https://openalex.org/W3198425604","https://openalex.org/W4206634335","https://openalex.org/W4310872040","https://openalex.org/W4320930577","https://openalex.org/W4391602018","https://openalex.org/W6600284362","https://openalex.org/W6610566761","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6638667902","https://openalex.org/W6640963894","https://openalex.org/W6666139384","https://openalex.org/W6674330103","https://openalex.org/W6675944832","https://openalex.org/W6680012447","https://openalex.org/W6681151457","https://openalex.org/W6687045409","https://openalex.org/W6718140377","https://openalex.org/W6730091202","https://openalex.org/W6731370813","https://openalex.org/W6746023985","https://openalex.org/W6774995033","https://openalex.org/W6780226713","https://openalex.org/W6802893474"],"related_works":["https://openalex.org/W1509813908","https://openalex.org/W2031820693","https://openalex.org/W1910172735","https://openalex.org/W2107364365","https://openalex.org/W2118307209","https://openalex.org/W2137288760","https://openalex.org/W2889447638","https://openalex.org/W2539388437","https://openalex.org/W2113403277","https://openalex.org/W1785857632"],"abstract_inverted_index":{"This":[0],"article":[1,178],"proposes":[2,179],"a":[3,27,39,44,101,180,189,235],"new":[4,181],"source":[5,32,40,79,118,135,157,203,213],"model":[6,41,136,158,182,204],"and":[7,14,48,124,188],"training":[8,190],"scheme":[9,191],"to":[10,76,115,164,230],"improve":[11,173],"the":[12,17,60,70,85,89,93,117,122,130,134,147,150,154,174,185,201,207],"accuracy":[13],"speed":[15],"of":[16,37,88,133,146,153],"multichannel":[18,31],"variational":[19],"autoencoder":[20],"(MVAE)":[21],"method.":[22,34],"The":[23,196],"MVAE":[24,71],"method":[25,72,102],"is":[26,62,84],"recently":[28],"proposed":[29,202,208],"powerful":[30],"separation":[33,51,80,214],"It":[35],"consists":[36],"pretraining":[38],"represented":[42],"by":[43],"conditional":[45],"VAE":[46,113],"(CVAE)":[47],"then":[49],"estimating":[50],"matrices":[52],"along":[53],"with":[54,169,206,216,234],"other":[55],"unknown":[56],"parameters":[57,132],"so":[58],"that":[59,200,225],"log-likelihood":[61],"non-decreasing":[63],"given":[64],"an":[65,110],"observed":[66],"mixture":[67],"signal.":[68],"Although":[69],"has":[73],"been":[74],"shown":[75],"provide":[77],"high":[78],"performance,":[81],"one":[82],"drawback":[83],"computational":[86],"cost":[87],"backpropagation":[90],"steps":[91],"in":[92,127,143,167],"separation-matrix":[94],"estimation":[95],"algorithm.":[96,148],"To":[97,172],"overcome":[98],"this":[99,128,177],"drawback,":[100],"called":[103],"\u201cFastMVAE\u201d":[104],"was":[105,159],"subsequently":[106],"proposed,":[107],"which":[108,162],"uses":[109],"auxiliary":[111],"classifier":[112,123],"(ACVAE)":[114],"train":[116],"model.":[119],"By":[120],"using":[121],"encoder":[125],"trained":[126,155,205],"way,":[129],"optimal":[131],"can":[137],"be":[138],"inferred":[139],"efficiently,":[140],"albeit":[141],"approximately,":[142],"each":[144],"step":[145],"However,":[149],"generalization":[151,175],"capability":[152],"ACVAE":[156],"not":[160],"satisfactory,":[161],"led":[163],"poor":[165],"performance":[166,215],"situations":[168],"unseen":[170],"data.":[171],"capability,":[176],"architecture":[183],"(called":[184],"\u201cChimeraACVAE\u201d":[186],"model)":[187],"based":[192],"on":[193],"knowledge":[194],"distillation.":[195],"experimental":[197],"results":[198],"revealed":[199],"loss":[209],"function":[210],"achieved":[211],"better":[212],"less":[217],"computation":[218],"time":[219],"than":[220],"FastMVAE.":[221],"We":[222],"also":[223],"confirmed":[224],"our":[226],"methods":[227],"were":[228],"able":[229],"separate":[231],"18":[232],"sources":[233],"reasonably":[236],"good":[237],"accuracy.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}