{"id":"https://openalex.org/W4283214653","doi":"https://doi.org/10.1109/infocom48880.2022.9796850","title":"DeepEar: Sound Localization with Binaural Microphones","display_name":"DeepEar: Sound Localization with Binaural Microphones","publication_year":2022,"publication_date":"2022-05-02","ids":{"openalex":"https://openalex.org/W4283214653","doi":"https://doi.org/10.1109/infocom48880.2022.9796850"},"language":"en","primary_location":{"id":"doi:10.1109/infocom48880.2022.9796850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom48880.2022.9796850","pdf_url":null,"source":{"id":"https://openalex.org/S4363607980","display_name":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","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":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","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/A5002167763","display_name":"Qiang Yang","orcid":null},"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":true,"raw_author_name":"Qiang Yang","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Computing,Hong Kong,China","Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Computing,Hong Kong,China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China","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":["The Hong Kong Polytechnic University,Department of Computing,Hong Kong,China","Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Computing,Hong Kong,China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002167763"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.9806,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76777251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"960","last_page":"969"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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":0.9955999851226807,"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/binaural-recording","display_name":"Binaural recording","score":0.8587132692337036},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7864003777503967},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6802831888198853},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.6241709589958191},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.6109599471092224},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5163037180900574},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.47333651781082153},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4677068591117859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4463891386985779},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4450306296348572},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.29716116189956665},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.27814459800720215},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.08537951111793518},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07968837022781372}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8587132692337036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864003777503967},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6802831888198853},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.6241709589958191},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.6109599471092224},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5163037180900574},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.47333651781082153},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4677068591117859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4463891386985779},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4450306296348572},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.29716116189956665},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.27814459800720215},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.08537951111793518},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07968837022781372},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/infocom48880.2022.9796850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom48880.2022.9796850","pdf_url":null,"source":{"id":"https://openalex.org/S4363607980","display_name":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","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":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W126779258","https://openalex.org/W1489347216","https://openalex.org/W1515109179","https://openalex.org/W1543582044","https://openalex.org/W1990760025","https://openalex.org/W2008806652","https://openalex.org/W2044623356","https://openalex.org/W2052036764","https://openalex.org/W2052163586","https://openalex.org/W2066689965","https://openalex.org/W2080985643","https://openalex.org/W2100471625","https://openalex.org/W2113638573","https://openalex.org/W2118889375","https://openalex.org/W2130942839","https://openalex.org/W2155323221","https://openalex.org/W2165698076","https://openalex.org/W2314523203","https://openalex.org/W2403149086","https://openalex.org/W2416573875","https://openalex.org/W2475311120","https://openalex.org/W2486913545","https://openalex.org/W2765962757","https://openalex.org/W2772736377","https://openalex.org/W2921741089","https://openalex.org/W2963339453","https://openalex.org/W2963659062","https://openalex.org/W3011890046","https://openalex.org/W3023214412","https://openalex.org/W3047213815","https://openalex.org/W3105684258","https://openalex.org/W3109382988","https://openalex.org/W3120755280","https://openalex.org/W3149717653","https://openalex.org/W3191982256","https://openalex.org/W4249479531","https://openalex.org/W6630456326","https://openalex.org/W6632499442","https://openalex.org/W6679436768","https://openalex.org/W6788879985"],"related_works":["https://openalex.org/W1991848873","https://openalex.org/W3004570917","https://openalex.org/W4389240440","https://openalex.org/W2084430325","https://openalex.org/W2041661331","https://openalex.org/W2539207221","https://openalex.org/W2045803470","https://openalex.org/W2242743481","https://openalex.org/W2809056180","https://openalex.org/W2015890751"],"abstract_inverted_index":{"Binaural":[0],"microphones,":[1],"referring":[2],"to":[3,31,58,82,116,155],"two":[4,89],"microphones":[5,46],"with":[6,33,44,60,87,158,179],"artificial":[7],"human-shaped":[8],"ears,":[9],"are":[10],"pervasively":[11],"used":[12,132],"in":[13,50,133,194],"humanoid":[14],"robots":[15,30],"and":[16,72,153,186],"hearing":[17],"aids":[18],"improving":[19],"sound":[20,41,85,181],"quality.":[21],"In":[22],"many":[23],"applications,":[24],"it":[25],"is":[26],"crucial":[27],"for":[28,142],"such":[29],"interact":[32],"humans":[34],"by":[35,92],"finding":[36],"the":[37,61,118,124,146,174],"voice":[38],"direction.":[39],"However,":[40,77],"source":[42],"localization":[43,63,101],"binaural":[45,99],"remains":[47],"challenging,":[48],"especially":[49],"multi-source":[51,62],"scenarios.":[52,196],"Prior":[53],"works":[54],"utilize":[55],"microphone":[56],"arrays":[57,66],"deal":[59],"problem.":[64],"Extra":[65],"yet":[67],"incur":[68],"higher":[69],"deployment":[70],"costs":[71],"take":[73],"up":[74],"more":[75],"space.":[76],"human":[78,125],"brains":[79],"have":[80],"evolved":[81],"locate":[83,105],"multiple":[84,106],"sources":[86],"only":[88],"ears.":[90],"Inspired":[91],"this":[93,109],"fact,":[94],"we":[95,111],"propose":[96],"DeepEar,":[97],"a":[98,113,159,180],"microphone-based":[100],"system":[102],"that":[103,169],"can":[104,137,150,171],"sounds.":[107],"To":[108],"end,":[110],"develop":[112],"neural":[114,148],"network":[115],"mimic":[117],"acoustic":[119],"signal":[120],"processing":[121],"pipeline":[122],"of":[123,162,184,191],"auditory":[126],"system.":[127],"Different":[128],"from":[129],"hand-crafted":[130],"features":[131,141],"prior":[134],"works,":[135],"DeepEar":[136,170],"automatically":[138],"extract":[139],"useful":[140],"localization.":[143],"More":[144],"importantly,":[145],"trained":[147],"networks":[149],"be":[151],"extended":[152],"adapted":[154],"new":[156],"environments":[157],"minimum":[160],"amount":[161],"extra":[163],"training":[164],"data.":[165],"Experiment":[166],"results":[167],"show":[168],"substantially":[172],"outperform":[173],"state-of-the-art":[175],"deep":[176],"learning":[177],"approach,":[178],"detection":[182],"accuracy":[183],"93.3%":[185],"an":[187],"azimuth":[188],"estimation":[189],"error":[190],"7.4":[192],"degrees":[193],"multisource":[195]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}