{"id":"https://openalex.org/W4310147672","doi":"https://doi.org/10.3390/sym14122514","title":"Multichannel Variational Autoencoder-Based Speech Separation in Designated Speaker Order","display_name":"Multichannel Variational Autoencoder-Based Speech Separation in Designated Speaker Order","publication_year":2022,"publication_date":"2022-11-28","ids":{"openalex":"https://openalex.org/W4310147672","doi":"https://doi.org/10.3390/sym14122514"},"language":"en","primary_location":{"id":"doi:10.3390/sym14122514","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym14122514","pdf_url":"https://www.mdpi.com/2073-8994/14/12/2514/pdf?version=1669639497","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/14/12/2514/pdf?version=1669639497","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049575911","display_name":"Lele Liao","orcid":"https://orcid.org/0000-0001-8801-1510"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lele Liao","raw_affiliation_strings":["Key Laboratory of Modern Acoustics, Institute of Acoustics, Nanjing University, Nanjing 210093, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Acoustics, Institute of Acoustics, Nanjing University, Nanjing 210093, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088747023","display_name":"Guoliang Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Cheng","raw_affiliation_strings":["Key Laboratory of Modern Acoustics, Institute of Acoustics, Nanjing University, Nanjing 210093, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Acoustics, Institute of Acoustics, Nanjing University, Nanjing 210093, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057903680","display_name":"Haoxin Ruan","orcid":"https://orcid.org/0000-0002-7093-4613"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxin Ruan","raw_affiliation_strings":["Key Laboratory of Modern Acoustics, Institute of Acoustics, Nanjing University, Nanjing 210093, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Acoustics, Institute of Acoustics, Nanjing University, Nanjing 210093, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437976","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0002-5624-2987"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Key Laboratory of Modern Acoustics, Institute of Acoustics, Nanjing University, Nanjing 210093, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Acoustics, Institute of Acoustics, Nanjing University, Nanjing 210093, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059632088","display_name":"Jing L\u00fc","orcid":"https://orcid.org/0000-0001-9683-3768"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Lu","raw_affiliation_strings":["Key Laboratory of Modern Acoustics, Institute of Acoustics, Nanjing University, Nanjing 210093, China"],"raw_orcid":"https://orcid.org/0000-0001-9683-3768","affiliations":[{"raw_affiliation_string":"Key Laboratory of Modern Acoustics, Institute of Acoustics, Nanjing University, Nanjing 210093, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059632088"],"corresponding_institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":0.2973,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52513966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"14","issue":"12","first_page":"2514","last_page":"2514"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9980999827384949,"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":0.8413774967193604},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7503076791763306},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7051866054534912},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.6208176016807556},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6183222532272339},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5625607371330261},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.46222981810569763},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.43700259923934937},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4320032596588135},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42162996530532837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4045442044734955},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2647712230682373}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8413774967193604},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7503076791763306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7051866054534912},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.6208176016807556},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6183222532272339},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5625607371330261},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.46222981810569763},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.43700259923934937},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4320032596588135},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42162996530532837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4045442044734955},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2647712230682373},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/sym14122514","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym14122514","pdf_url":"https://www.mdpi.com/2073-8994/14/12/2514/pdf?version=1669639497","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6108253acf784537a1e804a850604dd9","is_oa":true,"landing_page_url":"https://doaj.org/article/6108253acf784537a1e804a850604dd9","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":"Symmetry, Vol 14, Iss 12, p 2514 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2073-8994/14/12/2514/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/sym14122514","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/sym14122514","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym14122514","pdf_url":"https://www.mdpi.com/2073-8994/14/12/2514/pdf?version=1669639497","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G2966419421","display_name":"\u58f0\u5b66\u9635\u5217\u6297\u6270\u52a8\u7279\u6027\u5206\u6790\u4e0e\u6539\u8fdb\u65b9\u6cd5\u7814\u7a76","funder_award_id":"11874219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7049189742","display_name":null,"funder_award_id":"12274221","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4310147672.pdf","grobid_xml":"https://content.openalex.org/works/W4310147672.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W6639174","https://openalex.org/W285277413","https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1572099565","https://openalex.org/W1902027874","https://openalex.org/W1996304098","https://openalex.org/W2055637322","https://openalex.org/W2067295501","https://openalex.org/W2072548008","https://openalex.org/W2121812409","https://openalex.org/W2124486835","https://openalex.org/W2127851351","https://openalex.org/W2143486266","https://openalex.org/W2152049961","https://openalex.org/W2159466547","https://openalex.org/W2412956798","https://openalex.org/W2890964092","https://openalex.org/W2896495842","https://openalex.org/W2905196628","https://openalex.org/W2946521785","https://openalex.org/W2946555236","https://openalex.org/W2954049404","https://openalex.org/W2962866211","https://openalex.org/W2963375116","https://openalex.org/W2963969588","https://openalex.org/W2972593108","https://openalex.org/W2972659941","https://openalex.org/W2989942677","https://openalex.org/W3044124250","https://openalex.org/W3201588234","https://openalex.org/W4205778870","https://openalex.org/W6680012447"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W2166132814","https://openalex.org/W2951352292","https://openalex.org/W1005611038","https://openalex.org/W4298854296"],"abstract_inverted_index":{"The":[0,83,107,143,154],"multichannel":[1],"variational":[2],"autoencoder":[3],"(MVAE)":[4],"integrates":[5],"the":[6,14,28,59,63,66,70,73,77,80,88,96,100,104,122,126,158],"rule-based":[7],"update":[8],"of":[9,65,79],"a":[10,22,40,116],"separation":[11,25,152],"matrix":[12],"and":[13,18,35,69,87,133,137,150,162],"deep":[15],"generative":[16],"model":[17],"proves":[19],"to":[20,38,95,98,140],"be":[21,39],"competitive":[23],"speech":[24],"method.":[26],"However,":[27],"output":[29,67],"(global)":[30],"permutation":[31,118],"ambiguity":[32],"still":[33],"exists":[34],"turns":[36],"out":[37],"fundamental":[41],"problem":[42,51],"in":[43,112,129,173],"applications.":[44],"In":[45,121],"this":[46,50],"paper,":[47],"we":[48,124],"address":[49],"by":[52,115],"employing":[53],"two":[54],"dedicated":[55],"encoders.":[56],"One":[57],"encodes":[58,72],"speaker":[60,101],"identity":[61],"for":[62,76],"guidance":[64],"sorting,":[68],"other":[71,159],"linguistic":[74],"information":[75],"reconstruction":[78],"source":[81],"signals.":[82],"instance":[84,90],"normalization":[85,91],"(IN)":[86],"adaptive":[89],"(adaIN)":[92],"are":[93,110],"applied":[94],"networks":[97],"disentangle":[99],"representations":[102],"from":[103],"content":[105],"representations.":[106],"separated":[108],"sources":[109],"arranged":[111],"designated":[113],"order":[114],"symmetric":[117],"alignment":[119],"scheme.":[120],"experiments,":[123],"test":[125],"proposed":[127,155],"method":[128,156],"different":[130],"gender":[131],"combinations":[132],"various":[134],"reverberant":[135,175],"conditions":[136],"generalize":[138],"it":[139],"unseen":[141],"speakers.":[142],"results":[144],"validate":[145],"its":[146],"reliable":[147],"sorting":[148],"accuracy":[149],"good":[151],"performance.":[153],"outperforms":[157],"baseline":[160],"methods":[161],"maintains":[163],"stable":[164],"performance,":[165],"achieving":[166],"over":[167],"20":[168],"dB":[169],"SIR":[170],"improvement":[171],"even":[172],"high":[174],"environments.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}
