{"id":"https://openalex.org/W2897725921","doi":"https://doi.org/10.1109/acssc.2018.8645219","title":"A Performance Evaluation of Several Deep Neural Networks for Reverberant Speech Separation","display_name":"A Performance Evaluation of Several Deep Neural Networks for Reverberant Speech Separation","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2897725921","doi":"https://doi.org/10.1109/acssc.2018.8645219","mag":"2897725921"},"language":"en","primary_location":{"id":"doi:10.1109/acssc.2018.8645219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2018.8645219","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-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/A5074138677","display_name":"Qingju Liu","orcid":"https://orcid.org/0000-0003-2288-3417"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Qingju Liu","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022165330","display_name":"Philip J. B. Jackson","orcid":"https://orcid.org/0000-0001-7933-5935"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip J.B. Jackson","raw_affiliation_strings":["University of Surrey, Guildford, Surrey, GB"],"affiliations":[{"raw_affiliation_string":"University of Surrey, Guildford, Surrey, GB","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086899221","display_name":"Saeid Safavi","orcid":"https://orcid.org/0000-0002-3000-418X"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Saeid Safavi","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074138677"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":0.2382,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43264659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs 1412 6980","issue":null,"first_page":"689","last_page":"693"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.8654519319534302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7936098575592041},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6758207678794861},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6024423837661743},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5915865898132324},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5838376879692078},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5772733688354492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5244724750518799},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48602229356765747},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4365427494049072},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4351184368133545},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.42303597927093506},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39847251772880554},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06976878643035889}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.8654519319534302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7936098575592041},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6758207678794861},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6024423837661743},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5915865898132324},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5838376879692078},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5772733688354492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5244724750518799},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48602229356765747},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4365427494049072},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4351184368133545},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.42303597927093506},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39847251772880554},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06976878643035889},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/acssc.2018.8645219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2018.8645219","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11139965990002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:epubs.surrey.ac.uk:849431","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/849431/7/Asilomar2018.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3186182679","display_name":null,"funder_award_id":"EP/L000539/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1836465849","https://openalex.org/W1897240248","https://openalex.org/W1992879732","https://openalex.org/W2031647436","https://openalex.org/W2046317813","https://openalex.org/W2067295501","https://openalex.org/W2079735306","https://openalex.org/W2221409856","https://openalex.org/W2537586743","https://openalex.org/W2587994092","https://openalex.org/W2599685671","https://openalex.org/W2605138598","https://openalex.org/W2620812332","https://openalex.org/W2797579321","https://openalex.org/W2962866211","https://openalex.org/W2963703618","https://openalex.org/W2964121744","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6658463413","https://openalex.org/W6667372801","https://openalex.org/W6688843265","https://openalex.org/W6743446608","https://openalex.org/W6743462201","https://openalex.org/W6750531159"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2058482658","https://openalex.org/W2342810974","https://openalex.org/W2513767140","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W4386746628","https://openalex.org/W2037635165"],"abstract_inverted_index":{"In":[0,70,138],"this":[1],"paper,":[2],"we":[3],"compare":[4],"different":[5],"deep":[6],"neural":[7,29,33],"networks":[8],"(DNN)":[9],"in":[10,17,78,89,105],"extracting":[11],"speech":[12,125],"signals":[13],"from":[14],"competing":[15],"speakers":[16],"room":[18],"environments,":[19],"including":[20],"the":[21,37,63,90,98,102,116,122,128,135,144,149,153],"conventional":[22],"fully-connected":[23],"multilayer":[24],"perception":[25],"(MLP)":[26],"network,":[27],"convolutional":[28],"network":[30,34,41],"(CNN),":[31],"recurrent":[32],"(RNN),":[35],"and":[36,51,61,124],"recently":[38],"proposed":[39],"capsule":[40],"(CapsNet).":[42],"Each":[43],"DNN":[44,155],"takes":[45],"input":[46],"of":[47,85,107,127],"both":[48],"spectral":[49],"features":[50,54],"converted":[52],"spatial":[53],"that":[55],"are":[56,95],"robust":[57],"to":[58,134],"position":[59],"mismatch,":[60],"outputs":[62],"separation":[64],"mask":[65],"for":[66],"target":[67,130],"source":[68,131],"estimation.":[69],"addition,":[71],"a":[72],"psychacoustically-motivated":[73],"objective":[74],"function":[75],"is":[76],"integrated":[77],"each":[79,86],"DNN,":[80],"which":[81],"explores":[82],"perceptual":[83],"importance":[84],"TF":[87],"unit":[88],"training":[91],"process.":[92],"Objective":[93],"evaluations":[94],"performed":[96],"on":[97],"separated":[99],"sounds":[100],"using":[101],"converged":[103],"models,":[104],"terms":[106],"PESQ,":[108],"SDR":[109],"as":[110,112,132],"well":[111],"STOI.":[113],"Overall,":[114],"all":[115],"implemented":[117],"DNNs":[118],"have":[119],"greatly":[120],"improved":[121],"quality":[123],"intelligibility":[126],"embedded":[129],"compared":[133],"original":[136],"recordings.":[137],"particular,":[139],"bidirectional":[140],"RNN,":[141],"either":[142],"along":[143,148],"temporal":[145],"direction":[146],"or":[147],"frequency":[150],"bins,":[151],"outperforms":[152],"other":[154],"structures":[156],"with":[157],"consistent":[158],"improvement.":[159]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}