{"id":"https://openalex.org/W2304609584","doi":"https://doi.org/10.1109/taslp.2016.2536478","title":"A Deep Ensemble Learning Method for Monaural Speech Separation","display_name":"A Deep Ensemble Learning Method for Monaural Speech Separation","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2304609584","doi":"https://doi.org/10.1109/taslp.2016.2536478","mag":"2304609584","pmid":"https://pubmed.ncbi.nlm.nih.gov/27917394"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2536478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2536478","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","pubmed"],"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/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Center of Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":25.7578,"has_fulltext":false,"cited_by_count":230,"citation_normalized_percentile":{"value":0.99776516,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"24","issue":"5","first_page":"967","last_page":"977"},"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":0.9994000196456909,"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":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7899104356765747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7844817638397217},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6201618909835815},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5769263505935669},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5014955997467041},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.46904048323631287},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.46339088678359985},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43537938594818115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38802477717399597},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33460623025894165},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11320415139198303}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7899104356765747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7844817638397217},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6201618909835815},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5769263505935669},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5014955997467041},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.46904048323631287},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.46339088678359985},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43537938594818115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38802477717399597},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33460623025894165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11320415139198303},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2016.2536478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2536478","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"},{"id":"pmid:27917394","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27917394","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"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":null},{"id":"pmh:oai:europepmc.org:4087028","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5131883","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2910152985","display_name":null,"funder_award_id":"R01 DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G8822322065","display_name":null,"funder_award_id":"FA9550-12-1-0130","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W160800111","https://openalex.org/W1482149378","https://openalex.org/W1534477342","https://openalex.org/W1790748249","https://openalex.org/W1897240248","https://openalex.org/W1963970749","https://openalex.org/W1989954041","https://openalex.org/W2006129368","https://openalex.org/W2017608047","https://openalex.org/W2030885260","https://openalex.org/W2031647436","https://openalex.org/W2032252376","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2062227835","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2085191029","https://openalex.org/W2086139506","https://openalex.org/W2087368178","https://openalex.org/W2090681206","https://openalex.org/W2108597378","https://openalex.org/W2122982914","https://openalex.org/W2127851351","https://openalex.org/W2139622435","https://openalex.org/W2141998673","https://openalex.org/W2144763279","https://openalex.org/W2144786298","https://openalex.org/W2168231600","https://openalex.org/W2168379380","https://openalex.org/W2227273290","https://openalex.org/W2259731387","https://openalex.org/W2291877678","https://openalex.org/W2294745040","https://openalex.org/W2395156013","https://openalex.org/W2614085369","https://openalex.org/W3124794156","https://openalex.org/W3127686677","https://openalex.org/W4231807801","https://openalex.org/W6684859321","https://openalex.org/W6692000528","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2072124114","https://openalex.org/W2944394647","https://openalex.org/W1543248128"],"abstract_inverted_index":{"Monaural":[0],"speech":[1,9,16,23,76,157,196],"separation":[2,17],"is":[3,98,185,197],"a":[4,35,39,66,99,107],"fundamental":[5],"problem":[6],"in":[7,106,143,188],"robust":[8],"processing.":[10],"Recently,":[11],"deep":[12,67],"neural":[13],"network":[14,81,97],"(DNN)-based":[15],"methods,":[18],"which":[19],"predict":[20],"either":[21],"clean":[22,190,195],"or":[24],"an":[25],"ideal":[26,182],"time-frequency":[27,183],"mask,":[28],"have":[29,151,169],"demonstrated":[30],"remarkable":[31],"performance":[32],"improvement.":[33],"However,":[34],"single":[36],"DNN":[37,105],"with":[38,155],"given":[40],"window":[41,92],"length":[42],"does":[43],"not":[44,58],"leverage":[45],"contextual":[46],"information":[47],"sufficiently,":[48],"and":[49,119,132,177],"the":[50,53,83,110,113,122,126,134,138,141,144,162,165,172,181],"differences":[51],"between":[52],"two":[54,173],"optimization":[55,174],"objectives":[56,175],"are":[57],"well":[59],"understood.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64],"propose":[65],"ensemble":[68],"method,":[69],"named":[70],"multicontext":[71,80,96],"networks,":[72],"to":[73,200],"address":[74],"monaural":[75],"separation.":[77],"The":[78,94,159],"first":[79],"averages":[82],"outputs":[84],"of":[85,101,109,115,121,125,137,164],"multiple":[86,102],"DNNs":[87,142],"whose":[88],"inputs":[89],"employ":[90,147],"different":[91,148],"lengths.":[93],"second":[95],"stack":[100,111],"DNNs.":[103],"Each":[104],"module":[108,128,146],"takes":[112],"concatenation":[114],"original":[116],"acoustic":[117],"features":[118],"expansion":[120],"soft":[123],"output":[124],"lower":[127],"as":[129],"its":[130],"input,":[131],"predicts":[133],"ratio":[135],"mask":[136,184],"target":[139],"speaker;":[140],"same":[145],"contexts.":[149],"We":[150,168],"conducted":[152],"extensive":[153],"experiments":[154],"three":[156],"corpora.":[158],"results":[160],"demonstrate":[161],"effectiveness":[163],"proposed":[166],"method.":[167],"also":[170],"compared":[171],"systematically":[176],"found":[178],"that":[179],"predicting":[180,194],"more":[186],"efficient":[187],"utilizing":[189],"training":[191],"speech,":[192],"while":[193],"less":[198],"sensitive":[199],"SNR":[201],"variations.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":39},{"year":2019,"cited_by_count":34},{"year":2018,"cited_by_count":37},{"year":2017,"cited_by_count":27},{"year":2016,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}