{"id":"https://openalex.org/W2797579321","doi":"https://doi.org/10.1109/icassp.2018.8462603","title":"Iterative Deep Neural Networks for Speaker-Independent Binaural Blind Speech Separation","display_name":"Iterative Deep Neural Networks for Speaker-Independent Binaural Blind Speech Separation","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2797579321","doi":"https://doi.org/10.1109/icassp.2018.8462603","mag":"2797579321"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101467338","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-4944-6890"},"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":"Yong Xu","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 JB Jackson","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":"last","author":{"id":"https://openalex.org/A5054599395","display_name":"Peter John Cusack Coleman","orcid":"https://orcid.org/0000-0002-3266-7358"},"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 Coleman","raw_affiliation_strings":["Institute of Sound Recording, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Institute of Sound Recording, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5074138677"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":1.8242,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85996748,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"abs 1603 9382","issue":null,"first_page":"541","last_page":"545"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9993000030517578,"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":0.9966999888420105,"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/binaural-recording","display_name":"Binaural recording","score":0.8609013557434082},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7648274302482605},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7363446950912476},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.595809280872345},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5392995476722717},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.44213610887527466},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43182823061943054},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4316338002681732},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4268275797367096},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4059295654296875},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.2881295680999756}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8609013557434082},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7648274302482605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7363446950912476},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.595809280872345},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5392995476722717},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.44213610887527466},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43182823061943054},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4316338002681732},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4268275797367096},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4059295654296875},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2881295680999756},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2018.8462603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11139982820002346","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:846225","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/846225/1/2595LIU.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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G3034362336","display_name":null,"funder_award_id":"EP/P022529/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1790748249","https://openalex.org/W1836465849","https://openalex.org/W1897240248","https://openalex.org/W2031647436","https://openalex.org/W2046317813","https://openalex.org/W2067295501","https://openalex.org/W2078528584","https://openalex.org/W2101616935","https://openalex.org/W2168379380","https://openalex.org/W2194775991","https://openalex.org/W2221409856","https://openalex.org/W2331143823","https://openalex.org/W2408744528","https://openalex.org/W2599685671","https://openalex.org/W2620812332","https://openalex.org/W2949117887","https://openalex.org/W2962866211","https://openalex.org/W2963470893","https://openalex.org/W3124794156","https://openalex.org/W4300402905","https://openalex.org/W6638667902","https://openalex.org/W6658463413","https://openalex.org/W6667372801","https://openalex.org/W6687483927","https://openalex.org/W6688843265","https://openalex.org/W6701947533","https://openalex.org/W6727340567","https://openalex.org/W6738472138","https://openalex.org/W6743462201"],"related_works":["https://openalex.org/W3118578380","https://openalex.org/W4294326507","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3167935049","https://openalex.org/W3029198973","https://openalex.org/W185580640"],"abstract_inverted_index":{"In":[0,108],"this":[1],"paper,":[2],"we":[3],"propose":[4],"an":[5],"iterative":[6],"deep":[7],"neural":[8],"network":[9,75],"(DNN)-based":[10],"binaural":[11,36,98],"source":[12],"separation":[13],"scheme,":[14],"for":[15],"recovering":[16],"two":[17],"concurrent":[18],"speech":[19],"signals":[20],"in":[21,84],"a":[22,53,63,72],"room":[23],"environment.":[24],"Besides":[25],"the":[26,30,49,102,118],"commonly-used":[27],"spectral":[28],"features,":[29,99],"DNN":[31,50,57,104],"also":[32],"takes":[33],"non-linearly":[34],"wrapped":[35],"spatial":[37],"features":[38],"as":[39,69,71],"input,":[40],"which":[41],"are":[42],"refined":[43],"iteratively":[44],"using":[45,96],"parameters":[46],"estimated":[47],"from":[48],"output":[51],"via":[52],"feedback":[54],"loop.":[55],"Different":[56],"structures":[58],"have":[59],"been":[60],"tested,":[61],"including":[62],"classic":[64],"multilayer":[65],"perception":[66],"regression":[67],"architecture":[68,105],"well":[70],"new":[73],"hybrid":[74,103],"with":[76],"both":[77],"convolutional":[78],"and":[79,88,120],"densely-connected":[80],"layers.":[81],"Objective":[82],"evaluations":[83],"terms":[85],"of":[86],"PESQ":[87],"STOI":[89],"showed":[90],"consistent":[91],"improvement":[92],"over":[93],"baseline":[94],"methods":[95],"traditional":[97],"especially":[100],"when":[101],"was":[106],"employed.":[107],"addition,":[109],"our":[110],"proposed":[111],"scheme":[112],"is":[113],"robust":[114],"to":[115],"mismatches":[116],"between":[117],"training":[119],"testing":[121],"data.":[122]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}