{"id":"https://openalex.org/W2884424734","doi":"https://doi.org/10.1109/taslp.2018.2855960","title":"Robust Binaural Localization of a Target Sound Source by Combining Spectral Source Models and Deep Neural Networks","display_name":"Robust Binaural Localization of a Target Sound Source by Combining Spectral Source Models and Deep Neural Networks","publication_year":2018,"publication_date":"2018-07-13","ids":{"openalex":"https://openalex.org/W2884424734","doi":"https://doi.org/10.1109/taslp.2018.2855960","mag":"2884424734"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2855960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2855960","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.03006","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ning Ma","orcid":"https://orcid.org/0000-0002-4112-3109"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ning Ma","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, U.K"],"raw_orcid":"https://orcid.org/0000-0002-4112-3109","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, U.K","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jose A. Gonzalez","orcid":"https://orcid.org/0000-0002-5531-8994"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jose A. Gonzalez","raw_affiliation_strings":["University of Sheffield, Sheffield, U.K"],"raw_orcid":"https://orcid.org/0000-0002-5531-8994","affiliations":[{"raw_affiliation_string":"University of Sheffield, Sheffield, U.K","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":null,"display_name":"Guy J. Brown","orcid":"https://orcid.org/0000-0001-8565-5476"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guy J. Brown","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, U.K"],"raw_orcid":"https://orcid.org/0000-0001-8565-5476","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, U.K","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":4.5547,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.95544788,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"26","issue":"11","first_page":"2122","last_page":"2131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8457000255584717,"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":0.8457000255584717,"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":0.12200000137090683,"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/T11448","display_name":"Face recognition and analysis","score":0.004900000058114529,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6446999907493591},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.6384000182151794},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5412999987602234},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.48910000920295715},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4799000024795532},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4674000144004822},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4544000029563904},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.44929999113082886},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.44589999318122864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.765500009059906},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.6446999907493591},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.6384000182151794},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5412999987602234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5055999755859375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4959000051021576},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.48910000920295715},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4799000024795532},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.44589999318122864},{"id":"https://openalex.org/C2780665216","wikidata":"https://www.wikidata.org/wiki/Q6934498","display_name":"Multi-source","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C2985998994","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Source model","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.40119999647140503},{"id":"https://openalex.org/C2778095710","wikidata":"https://www.wikidata.org/wiki/Q6031225","display_name":"Information source (mathematics)","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.3070000112056732},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2018.2855960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2855960","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":"pmh:oai:arXiv.org:1904.03006","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03006","pdf_url":"https://arxiv.org/pdf/1904.03006","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":{"id":"pmh:oai:arXiv.org:1904.03006","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03006","pdf_url":"https://arxiv.org/pdf/1904.03006","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1591446137","https://openalex.org/W1800365115","https://openalex.org/W1933749547","https://openalex.org/W1989954041","https://openalex.org/W2014894389","https://openalex.org/W2015143272","https://openalex.org/W2044222806","https://openalex.org/W2049633694","https://openalex.org/W2056907562","https://openalex.org/W2060741034","https://openalex.org/W2076266454","https://openalex.org/W2096740310","https://openalex.org/W2106603795","https://openalex.org/W2113067468","https://openalex.org/W2114218864","https://openalex.org/W2119901478","https://openalex.org/W2129171989","https://openalex.org/W2129697784","https://openalex.org/W2155323221","https://openalex.org/W2166682639","https://openalex.org/W2170864449","https://openalex.org/W2569282529","https://openalex.org/W2765962757","https://openalex.org/W4256399001","https://openalex.org/W6600355267","https://openalex.org/W6630456326","https://openalex.org/W6652194891","https://openalex.org/W6713759684","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W2952874706","https://openalex.org/W3011070339","https://openalex.org/W2025382336","https://openalex.org/W2067878257","https://openalex.org/W1602847930","https://openalex.org/W3159094331","https://openalex.org/W4243334934","https://openalex.org/W2086405957","https://openalex.org/W2364764608","https://openalex.org/W2622820612"],"abstract_inverted_index":{"Despite":[0],"there":[1],"being":[2],"a":[3,35,65,73,95,128,142,180,190],"clear":[4],"evidence":[5],"for":[6,38],"top-down":[7,22],"(e.g.,":[8],"attentional)":[9],"effects":[10],"in":[11,25,83,164,194,213],"biological":[12],"spatial":[13],"hearing,":[14],"relatively":[15],"few":[16],"machine":[17],"hearing":[18],"systems":[19],"exploit":[20],"the":[21,39,45,49,86,89,104,112,117,134,138,149,155,161,173,195,210,216],"model-based":[23,46,174,211],"knowledge":[24],"sound":[26,41,53,81,217],"localization.":[27],"This":[28],"paper":[29],"addresses":[30],"this":[31,214],"issue":[32],"by":[33,120,127,208],"proposing":[34],"novel":[36],"framework":[37],"binaural":[40],"localization":[42,118,130,188,218],"that":[43,207],"combines":[44,172],"information":[47,177,212],"about":[48],"spectral":[50,77],"characteristics":[51],"of":[52,88,189,197],"sources":[54],"and":[55,64,115,140,175,201,227],"deep":[56],"neural":[57],"networks":[58],"(DNNs).":[59],"A":[60],"target":[61,191],"source":[62,67,91,105,123,193,200],"model":[63,68,98,143,157],"background":[66,90,97,156],"are":[69,107],"first":[70],"estimated":[71],"during":[72,151],"training":[74,139],"phase":[75],"using":[76],"features":[78],"extracted":[79],"from":[80,160],"signals":[82],"isolation.":[84],"When":[85],"identity":[87],"is":[92,146],"not":[93],"available,":[94],"universal":[96],"can":[99,220],"be":[100,221],"used.":[101],"During":[102],"testing,":[103,141,152],"models":[106],"used":[108],"jointly":[109],"to":[110],"explain":[111],"mixed":[113],"observations":[114,163],"improve":[116],"process":[119,145],"selectively":[121],"weighting":[122],"azimuth":[124],"posteriors":[125],"output":[126],"DNN-based":[129],"system.":[131],"To":[132],"address":[133],"possible":[135],"mismatch":[136],"between":[137],"adaptation":[144],"further":[147],"employed":[148],"on-the-fly":[150],"which":[153],"adapts":[154],"parameters":[158],"directly":[159],"noisy":[162,226],"an":[165,198],"iterative":[166],"manner.":[167],"The":[168,184],"proposed":[169],"system,":[170],"therefore,":[171],"data-driven":[176],"flow":[178],"within":[179],"single":[181],"computational":[182],"framework.":[183],"evaluation":[185],"task":[186],"involved":[187],"speech":[192],"presence":[196],"interfering":[199],"room":[202],"reverberation.":[203],"Our":[204],"experiments":[205],"show":[206],"exploiting":[209],"way,":[215],"performance":[219],"improved":[222],"substantially":[223],"under":[224],"various":[225],"reverberant":[228],"conditions.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":8}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2018-08-03T00:00:00"}