{"id":"https://openalex.org/W4312873392","doi":"https://doi.org/10.1109/tmc.2022.3222821","title":"DeepEar: Sound Localization With Binaural Microphones","display_name":"DeepEar: Sound Localization With Binaural Microphones","publication_year":2022,"publication_date":"2022-11-17","ids":{"openalex":"https://openalex.org/W4312873392","doi":"https://doi.org/10.1109/tmc.2022.3222821"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2022.3222821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2022.3222821","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Transactions on Mobile Computing","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/A5023276909","display_name":"Qiang Yang","orcid":"https://orcid.org/0000-0002-5202-7892"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qiang Yang","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-5202-7892","affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091556511","display_name":"Yuanqing Zheng","orcid":"https://orcid.org/0000-0003-3096-687X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuanqing Zheng","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-3096-687X","affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":1.8382,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85494099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"23","issue":"1","first_page":"359","last_page":"375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9937999844551086,"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":0.9902999997138977,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.8593816757202148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8018749356269836},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.6848379373550415},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6803700923919678},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5520081520080566},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5050726532936096},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.4945847690105438},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4903857707977295},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.48845067620277405},{"id":"https://openalex.org/keywords/surround-sound","display_name":"Surround sound","score":0.4675665497779846},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.4352349638938904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3405213952064514},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.32997363805770874},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1358388066291809},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.13152414560317993}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8593816757202148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8018749356269836},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.6848379373550415},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6803700923919678},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5520081520080566},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5050726532936096},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.4945847690105438},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4903857707977295},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.48845067620277405},{"id":"https://openalex.org/C2780544925","wikidata":"https://www.wikidata.org/wiki/Q569874","display_name":"Surround sound","level":3,"score":0.4675665497779846},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.4352349638938904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3405213952064514},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.32997363805770874},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1358388066291809},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.13152414560317993},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmc.2022.3222821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2022.3222821","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Transactions on Mobile Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6200000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W79714967","https://openalex.org/W126779258","https://openalex.org/W1489347216","https://openalex.org/W1505940748","https://openalex.org/W1515109179","https://openalex.org/W1518870451","https://openalex.org/W1543582044","https://openalex.org/W1635512741","https://openalex.org/W1974387177","https://openalex.org/W1990760025","https://openalex.org/W1997669607","https://openalex.org/W2008806652","https://openalex.org/W2015792005","https://openalex.org/W2050758723","https://openalex.org/W2052036764","https://openalex.org/W2052163586","https://openalex.org/W2056951869","https://openalex.org/W2080985643","https://openalex.org/W2100471625","https://openalex.org/W2106325442","https://openalex.org/W2113638573","https://openalex.org/W2116101591","https://openalex.org/W2118889375","https://openalex.org/W2128977628","https://openalex.org/W2130459697","https://openalex.org/W2139190150","https://openalex.org/W2141641465","https://openalex.org/W2155323221","https://openalex.org/W2163320322","https://openalex.org/W2163344649","https://openalex.org/W2165698076","https://openalex.org/W2314292396","https://openalex.org/W2314523203","https://openalex.org/W2416573875","https://openalex.org/W2475311120","https://openalex.org/W2486913545","https://openalex.org/W2535255545","https://openalex.org/W2765962757","https://openalex.org/W2772736377","https://openalex.org/W2885219692","https://openalex.org/W2896339047","https://openalex.org/W2901937441","https://openalex.org/W2917254586","https://openalex.org/W2921741089","https://openalex.org/W2947942791","https://openalex.org/W2963339453","https://openalex.org/W2963659062","https://openalex.org/W2964338223","https://openalex.org/W3011890046","https://openalex.org/W3023214412","https://openalex.org/W3095212293","https://openalex.org/W3105684258","https://openalex.org/W3109382988","https://openalex.org/W3132830522","https://openalex.org/W3188274837","https://openalex.org/W3191982256","https://openalex.org/W3197097128","https://openalex.org/W3208826591","https://openalex.org/W4233385860","https://openalex.org/W4249479531","https://openalex.org/W4393790520","https://openalex.org/W6630456326","https://openalex.org/W6632499442","https://openalex.org/W6638676062","https://openalex.org/W6659313619","https://openalex.org/W6679436768","https://openalex.org/W6756622180","https://openalex.org/W6776646455","https://openalex.org/W6788879985","https://openalex.org/W6802810599","https://openalex.org/W6864030627"],"related_works":["https://openalex.org/W3011070339","https://openalex.org/W2108013559","https://openalex.org/W2126980866","https://openalex.org/W2288611238","https://openalex.org/W2120264472","https://openalex.org/W3080770005","https://openalex.org/W2377537305","https://openalex.org/W4386900535","https://openalex.org/W2271701291","https://openalex.org/W2912446729"],"abstract_inverted_index":{"The":[0,183],"binaural":[1,44,115,193],"microphone,":[2],"which":[3],"refers":[4],"to":[5,24,34,65,102,129,160,172],"a":[6,114,125,139,176,198],"pair":[7],"of":[8,142,148,179,203],"microphones":[9,52,73],"with":[10,50,67,107,175],"artificial":[11],"human-shaped":[12],"ears,":[13,110],"is":[14,29,138],"widely":[15],"used":[16],"in":[17,39,56,80,201],"hearing":[18,92],"aids":[19],"and":[20,155,207],"spatial":[21],"audio":[22],"recording":[23],"improve":[25],"sound":[26,45,48,105,117,132,158,162,204],"quality.":[27],"It":[28],"crucial":[30],"for":[31,78,145],"such":[32,42],"devices":[33],"find":[35],"the":[36,68,96,143,166,191],"voice":[37],"direction":[38],"many":[40,81],"applications":[41],"as":[43],"enhancement.":[46],"However,":[47],"localization":[49,70,118],"two":[51,109],"remains":[53],"challenging,":[54],"especially":[55],"multi-source":[57,69],"scenarios.":[58],"Most":[59],"previous":[60],"work":[61],"utilized":[62],"microphone":[63],"arrays":[64],"deal":[66],"problem.":[71],"Extra":[72],"yet":[74],"have":[75,100],"space":[76,144],"constraints":[77],"deployment":[79],"scenarios":[82],"(":[83],"<italic":[84,88],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[85,89],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">e</i>":[86],".":[87],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">g</i>":[90],".,":[91],"aids).":[93],"Inspired":[94],"by":[95,197],"fact":[97],"that":[98,187],"humans":[99],"evolved":[101],"locate":[103,130],"multiple":[104,131],"sources":[106,133],"only":[108],"we":[111,123],"propose":[112],"DeepEar,":[113],"microphone-based":[116],"system.":[119],"To":[120],"this":[121],"end,":[122],"design":[124],"multisector-based":[126],"neural":[127],"network":[128],"simultaneously,":[134],"where":[135],"each":[136],"sector":[137],"discretized":[140],"region":[141],"different":[146],"angle":[147],"arrivals.":[149],"DeepEar":[150,168,188],"fuses":[151],"explicit":[152],"hand-crafted":[153],"features":[154],"implicit":[156],"latent":[157],"representatives":[159],"facilitate":[161],"localization.":[163],"More":[164],"importantly,":[165],"trained":[167],"model":[169],"can":[170],"adapt":[171],"new":[173],"environments":[174],"minimum":[177],"amount":[178],"extra":[180],"training":[181],"data.":[182],"experiment":[184],"results":[185],"show":[186],"substantially":[189],"outperforms":[190],"state-of-the-art":[192],"deep":[194],"learning":[195],"approach":[196],"large":[199],"margin":[200],"terms":[202],"detection":[205],"accuracy":[206],"azimuth":[208],"estimation":[209],"error.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}