{"id":"https://openalex.org/W3029436999","doi":"https://doi.org/10.1186/s13636-020-0171-y","title":"Binaural sound localization based on deep neural network and affinity propagation clustering in mismatched HRTF condition","display_name":"Binaural sound localization based on deep neural network and affinity propagation clustering in mismatched HRTF condition","publication_year":2020,"publication_date":"2020-02-10","ids":{"openalex":"https://openalex.org/W3029436999","doi":"https://doi.org/10.1186/s13636-020-0171-y","mag":"3029436999"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-020-0171-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-020-0171-y","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-020-0171-y","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-020-0171-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100378497","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0002-3653-9951"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Wang","raw_affiliation_strings":["Beijing Institute of Technology, 5 South Zhongguancun Street, Beijing, 100081, China"],"raw_orcid":"https://orcid.org/0000-0002-3653-9951","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, 5 South Zhongguancun Street, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100694383","display_name":"Jin Wang","orcid":"https://orcid.org/0000-0001-5437-3150"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Wang","raw_affiliation_strings":["Beijing Institute of Technology, 5 South Zhongguancun Street, Beijing, 100081, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, 5 South Zhongguancun Street, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102803079","display_name":"Kai Qian","orcid":"https://orcid.org/0000-0002-2112-1819"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Qian","raw_affiliation_strings":["Beijing Institute of Technology, 5 South Zhongguancun Street, Beijing, 100081, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, 5 South Zhongguancun Street, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100642395","display_name":"Xiang Xie","orcid":"https://orcid.org/0000-0002-5135-0110"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Xie","raw_affiliation_strings":["Beijing Institute of Technology, 5 South Zhongguancun Street, Beijing, 100081, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, 5 South Zhongguancun Street, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103540968","display_name":"Jingming Kuang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingming Kuang","raw_affiliation_strings":["Beijing Institute of Technology, 5 South Zhongguancun Street, Beijing, 100081, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, 5 South Zhongguancun Street, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100378497"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":3.9506,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.94487983,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"2020","issue":"1","first_page":null,"last_page":null},"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":0.9994999766349792,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/binaural-recording","display_name":"Binaural recording","score":0.882642388343811},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7186113595962524},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.620222270488739},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5758211612701416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5463933348655701},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5358923673629761},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5175092220306396},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.511676549911499},{"id":"https://openalex.org/keywords/head-related-transfer-function","display_name":"Head-related transfer function","score":0.5096015930175781},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4994213581085205},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4916549324989319},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.48026394844055176},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.47350364923477173},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13958051800727844},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10860961675643921}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.882642388343811},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7186113595962524},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.620222270488739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5758211612701416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5463933348655701},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5358923673629761},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5175092220306396},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.511676549911499},{"id":"https://openalex.org/C151382886","wikidata":"https://www.wikidata.org/wiki/Q1432854","display_name":"Head-related transfer function","level":3,"score":0.5096015930175781},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4994213581085205},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4916549324989319},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.48026394844055176},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.47350364923477173},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13958051800727844},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10860961675643921},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-020-0171-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-020-0171-y","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-020-0171-y","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:885ae292858a48acb905bf07b28d6813","is_oa":true,"landing_page_url":"https://doaj.org/article/885ae292858a48acb905bf07b28d6813","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2020, Iss 1, Pp 1-16 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-020-0171-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-020-0171-y","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-020-0171-y","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3126423603","display_name":null,"funder_award_id":"No. 11590772","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5050331986","display_name":null,"funder_award_id":"61571044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5541428379","display_name":null,"funder_award_id":"11590772","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8379179523","display_name":null,"funder_award_id":"No. 61571044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3029436999.pdf","grobid_xml":"https://content.openalex.org/works/W3029436999.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1635512741","https://openalex.org/W1792834816","https://openalex.org/W1904365287","https://openalex.org/W1987906574","https://openalex.org/W1992110312","https://openalex.org/W1993598632","https://openalex.org/W2012858128","https://openalex.org/W2034040413","https://openalex.org/W2044222806","https://openalex.org/W2046317813","https://openalex.org/W2062227835","https://openalex.org/W2086110556","https://openalex.org/W2100668143","https://openalex.org/W2105405275","https://openalex.org/W2106925337","https://openalex.org/W2108668360","https://openalex.org/W2113638573","https://openalex.org/W2128131274","https://openalex.org/W2149961907","https://openalex.org/W2153248083","https://openalex.org/W2155323221","https://openalex.org/W2165408050","https://openalex.org/W2416573875","https://openalex.org/W2561557072","https://openalex.org/W2615100522","https://openalex.org/W2765962757","https://openalex.org/W2801757532","https://openalex.org/W2809056180","https://openalex.org/W2921741089","https://openalex.org/W2963339453","https://openalex.org/W3127686677","https://openalex.org/W4233392025"],"related_works":["https://openalex.org/W2622611424","https://openalex.org/W4221151007","https://openalex.org/W4366826909","https://openalex.org/W2507744892","https://openalex.org/W1551351586","https://openalex.org/W1989632033","https://openalex.org/W593217055","https://openalex.org/W4232268940","https://openalex.org/W1482972934","https://openalex.org/W2093409968"],"abstract_inverted_index":{"Abstract":[0],"Binaural":[1],"sound":[2,71,169],"source":[3,170],"localization":[4,58,102,152,171,193,212,226],"is":[5,35,92,110,222,319],"an":[6],"important":[7],"and":[8,14,87,147,167,183,270,299],"widely":[9],"used":[10,82,179],"perceptually":[11],"based":[12,26,141],"method":[13,140,285,318],"it":[15],"has":[16,300],"been":[17],"applied":[18],"to":[19,38,51,54,83,98,107,111,115,149,180,264,271,304],"machine":[20,48],"learning":[21,49],"studies":[22,50],"by":[23,199],"many":[24],"researchers":[25],"on":[27,56,142,203,218,231],"head-related":[28],"transfer":[29],"function":[30],"(HRTF).":[31],"Because":[32],"the":[33,42,80,85,126,155,162,168,192,211,215,225,232,255,283,291,295,305,316],"HRTF":[34,76,157,297],"closely":[36],"related":[37],"human":[39],"physiological":[40],"structure,":[41],"HRTFs":[43,81,177,248,257],"vary":[44],"between":[45,164],"individuals.":[46],"Related":[47],"date":[52],"tend":[53],"focus":[55],"binaural":[57,151,165],"in":[59,65,78,131,154,294],"reverberant":[60],"or":[61,64],"noisy":[62],"environments,":[63],"conditions":[66],"with":[67,172,308],"multiple":[68],"simultaneously":[69],"active":[70],"sources.":[72],"In":[73,133],"contrast,":[74],"mismatched":[75,156,296],"condition,":[77],"which":[79,119,314],"generate":[84,181,265],"training":[86,182,201,268],"test":[88,184,205,220,234],"sets":[89,221],"are":[90,178,249,262],"different,":[91,223],"rarely":[93],"studied.":[94],"This":[95],"mismatch":[96],"leads":[97],"a":[99,121,138,173,243,266,273,309],"degradation":[100],"of":[101,195,214,228,258,312],"performance.":[103],"A":[104],"basic":[105],"solution":[106],"this":[108,134,188],"problem":[109],"introduce":[112],"more":[113,274],"data":[114,127],"improve":[116,150],"generalization":[117,288],"performance,":[118],"requires":[120],"lot.":[122],"However,":[123],"simply":[124],"increasing":[125],"volume":[128],"will":[129],"result":[130,208,240],"data-inefficiency.":[132],"paper,":[135],"we":[136,160,190],"propose":[137],"data-efficient":[139],"deep":[143],"neural":[144],"network":[145],"(DNN)":[146],"clustering":[148,244],"performance":[153,194,213,227,289,303],"condition.":[158],"Firstly,":[159],"analyze":[161],"relationship":[163],"cues":[166],"classification":[174],"DNN.":[175],"Different":[176],"sets,":[185],"respectively.":[186],"On":[187],"basis,":[189],"study":[191],"DNN":[196,276,306],"model":[197,217],"trained":[198,307],"each":[200,259],"set":[202,235,269],"different":[204,219,229,247],"sets.":[206],"The":[207,239,278],"shows":[209,242],"that":[210,282],"same":[216,233],"while":[224],"models":[230],"may":[236],"be":[237],"similar.":[238],"also":[241],"trend.":[245],"Secondly,":[246],"divided":[250],"into":[251],"several":[252],"clusters.":[253],"Finally,":[254],"corresponding":[256],"cluster":[260],"center":[261],"selected":[263],"new":[267],"train":[272],"generalized":[275],"model.":[277],"experimental":[279],"results":[280],"show":[281],"proposed":[284,317],"achieves":[286],"better":[287],"than":[290],"baseline":[292],"methods":[293],"condition":[298],"almost":[301],"equal":[302],"large":[310],"number":[311],"HRTFs,":[313],"means":[315],"data-efficient.":[320]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}