{"id":"https://openalex.org/W2791874741","doi":"https://doi.org/10.1109/taslp.2018.2817798","title":"A Multiobjective Learning and Ensembling Approach to High-Performance Speech Enhancement With Compact Neural Network Architectures","display_name":"A Multiobjective Learning and Ensembling Approach to High-Performance Speech Enhancement With Compact Neural Network Architectures","publication_year":2018,"publication_date":"2018-03-23","ids":{"openalex":"https://openalex.org/W2791874741","doi":"https://doi.org/10.1109/taslp.2018.2817798","mag":"2791874741"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2817798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2817798","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/A5100434900","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0003-3843-3920"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, CN"],"raw_orcid":"https://orcid.org/0000-0003-3843-3920","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, CN","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, CN"],"raw_orcid":"https://orcid.org/0000-0002-2387-0389","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, CN","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, CN","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, US","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":3.9634,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.94744727,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"26","issue":"7","first_page":"1185","last_page":"1197"},"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":0.9972000122070312,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7571524381637573},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7100160717964172},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.636583685874939},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5628383159637451},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5548914074897766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.550902783870697},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5098559260368347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5067203640937805},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48849403858184814},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48571500182151794},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.46721139550209045},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4285500645637512},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3169722855091095},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.310281366109848}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7571524381637573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7100160717964172},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.636583685874939},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5628383159637451},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5548914074897766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.550902783870697},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5098559260368347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5067203640937805},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48849403858184814},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48571500182151794},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.46721139550209045},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4285500645637512},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3169722855091095},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.310281366109848},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2817798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2817798","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":[{"id":"https://openalex.org/G573022218","display_name":null,"funder_award_id":"U1613211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8173470123","display_name":"\u57fa\u4e8e\u56de\u5f52\u795e\u7ecf\u7f51\u7edc\u7684\u8bed\u97f3\u5206\u79bb\u5173\u952e\u95ee\u9898\u7814\u7a76","funder_award_id":"61671422","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W190004713","https://openalex.org/W258661521","https://openalex.org/W1495679096","https://openalex.org/W1527498845","https://openalex.org/W1552314771","https://openalex.org/W1766888123","https://openalex.org/W1790748249","https://openalex.org/W1815076433","https://openalex.org/W1904365287","https://openalex.org/W1974387177","https://openalex.org/W1995536493","https://openalex.org/W2013608223","https://openalex.org/W2023331723","https://openalex.org/W2034040413","https://openalex.org/W2035576074","https://openalex.org/W2044893557","https://openalex.org/W2062164080","https://openalex.org/W2078528584","https://openalex.org/W2093717447","https://openalex.org/W2096698681","https://openalex.org/W2102346872","https://openalex.org/W2103075368","https://openalex.org/W2115055618","https://openalex.org/W2121973264","https://openalex.org/W2125610452","https://openalex.org/W2125630648","https://openalex.org/W2126942983","https://openalex.org/W2128653836","https://openalex.org/W2130476329","https://openalex.org/W2141493634","https://openalex.org/W2141892084","https://openalex.org/W2141998673","https://openalex.org/W2146324387","https://openalex.org/W2148154194","https://openalex.org/W2161025448","https://openalex.org/W2164432048","https://openalex.org/W2165712214","https://openalex.org/W2168379380","https://openalex.org/W2181607856","https://openalex.org/W2290318471","https://openalex.org/W2304609584","https://openalex.org/W2312381234","https://openalex.org/W2397226255","https://openalex.org/W2398723458","https://openalex.org/W2402922286","https://openalex.org/W2403766732","https://openalex.org/W2406737436","https://openalex.org/W2478884216","https://openalex.org/W2516342150","https://openalex.org/W2517760955","https://openalex.org/W2561557072","https://openalex.org/W2605589342","https://openalex.org/W2606806821","https://openalex.org/W2698117193","https://openalex.org/W2755891984","https://openalex.org/W2914048585","https://openalex.org/W3004732066","https://openalex.org/W3124794156","https://openalex.org/W3127686677","https://openalex.org/W3147539069","https://openalex.org/W4253928870","https://openalex.org/W6631567105","https://openalex.org/W6638545294","https://openalex.org/W6640036494","https://openalex.org/W6675700563","https://openalex.org/W6679009796","https://openalex.org/W6686045668","https://openalex.org/W6696830301","https://openalex.org/W6712317276","https://openalex.org/W6713298849","https://openalex.org/W6744261651","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W334008168","https://openalex.org/W2535773091"],"abstract_inverted_index":{"In":[0],"this":[1,217],"study,":[2],"we":[3],"propose":[4],"a":[5,17,26,48,85,141,187,243,248],"novel":[6],"deep":[7],"neural":[8],"network":[9],"(DNN)":[10],"architecture":[11],"for":[12,219],"speech":[13,91,166],"enhancement":[14],"(SE)":[15],"via":[16],"multiobjective":[18,61,86,105],"learning":[19,62],"and":[20,28,51,77,96,117,122,126,128,131,162,191,202,229,251,272],"ensembling":[21,106],"(MOLE)":[22],"framework":[23],"to":[24,83,147],"achieve":[25,196],"compact":[27,55],"lowlatency":[29],"design,":[30],"while":[31],"maintaining":[32],"good":[33],"performance":[34,255],"in":[35,174,208,216],"quality":[36],"evaluations.":[37],"MOLE":[38,183],"follows":[39],"the":[40,60,104,110,148,154,160,163,177,182,212,238,257],"boosting":[41],"concept":[42],"when":[43],"combining":[44],"weak":[45,137],"models":[46],"into":[47],"strong":[49],"classifier":[50],"consists":[52],"of":[53,136,210],"two":[54],"DNNs.":[56],"The":[57,101,232],"first,":[58],"called":[59,103],"DNN":[63,107],"(MOL-DNN),":[64],"takes":[65,109],"multiple":[66,155],"features,":[67],"such":[68],"as":[69,115],"log-power":[70],"spectra":[71],"(LPS),":[72],"mel-frequency":[73],"cepstral":[74,80],"coefficients":[75,81],"(MFCCs)":[76],"Gammatone":[78],"frequency":[79],"(GFCCs)":[82],"predict":[84],"set":[87],"that":[88,181],"includes":[89],"clean":[90,120,124,129,150],"feature,":[92,95],"dynamic":[93],"noise":[94,170],"ideal":[97],"ratio":[98],"mask":[99],"(IRM).":[100],"second,":[102],"(MOE-DNN),":[108],"learned":[111,157],"features":[112,151,186],"from":[113,158],"MOL-DNN":[114,161],"inputs":[116],"separately":[118],"predicts":[119],"LPS":[121],"IRM,":[123,127],"MFCC":[125],"GFCC":[130],"IRM":[132],"using":[133],"three":[134,221],"sets":[135],"regression":[138],"functions.":[139],"Finally,":[140],"postprocessing":[142],"operation":[143],"can":[144,195],"be":[145],"applied":[146],"estimated":[149],"by":[152,168,266],"leveraging":[153],"targets":[156],"both":[159,200],"MOE-DNN.":[164],"On":[165],"corrupted":[167],"15":[169],"types":[171],"not":[172],"seen":[173],"model":[175,189],"training":[176],"SE":[178,235,240,259],"results":[179],"show":[180],"approach,":[184],"which":[185],"small":[188],"size":[190],"low":[192],"run-time":[193],"latency,":[194],"consistent":[197],"improvements":[198],"over":[199],"DNN-":[201],"long":[203],"short-term":[204],"memory":[205],"(LSTM)-based":[206],"techniques":[207],"terms":[209],"all":[211,220],"objective":[213],"metrics":[214],"evaluated":[215],"study":[218],"cases":[222],"(the":[223],"input":[224,245],"contexts":[225],"contain":[226],"1-frame,":[227],"4-frame":[228],"7-frame":[230,244],"instances).":[231],"1-frame":[233],"MOLE-based":[234],"system":[236,241,260],"outperforms":[237],"DNN-based":[239],"with":[242,261,273],"expansion":[246,265],"at":[247],"3-frame":[249],"delay":[250,264],"also":[252],"achieves":[253],"better":[254],"than":[256],"LSTM-based":[258],"4-frame,":[262],"no":[263],"including":[267],"only":[268],"3":[269],"previous":[270],"frames,":[271],"170":[274],"times":[275],"less":[276],"processing":[277],"latency.":[278]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}