{"id":"https://openalex.org/W1596338834","doi":"https://doi.org/10.1109/icassp.2015.7178452","title":"Binaural localization of speech sources in 3-D using a composite feature vector of the HRTF","display_name":"Binaural localization of speech sources in 3-D using a composite feature vector of the HRTF","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1596338834","doi":"https://doi.org/10.1109/icassp.2015.7178452","mag":"1596338834"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5091170889","display_name":"Xiang Wu","orcid":"https://orcid.org/0000-0001-5190-9781"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiang Wu","raw_affiliation_strings":["Research School of Engineering CECS, The Australian National University, Canberra, Australia","Research School of Engineering, CECS, The Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research School of Engineering CECS, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Research School of Engineering, CECS, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061069299","display_name":"Dumidu S. Talagala","orcid":"https://orcid.org/0000-0002-8210-932X"},"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":"Dumidu S. Talagala","raw_affiliation_strings":["CVSSP, University of Surrey, Guildford, United Kingdom","[CVSSP, University of Surrey, Guildford, United Kingdom]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVSSP, University of Surrey, Guildford, United Kingdom","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"[CVSSP, University of Surrey, Guildford, United Kingdom]","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059258204","display_name":"Wen Zhang","orcid":"https://orcid.org/0000-0002-0752-6123"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wen Zhang","raw_affiliation_strings":["Research School of Engineering CECS, The Australian National University, Canberra, Australia","Research School of Engineering, CECS, The Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research School of Engineering CECS, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Research School of Engineering, CECS, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003018152","display_name":"Thushara D. Abhayapala","orcid":"https://orcid.org/0000-0001-6937-7218"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Thushara D. Abhayapala","raw_affiliation_strings":["Research School of Engineering CECS, The Australian National University, Canberra, Australia","Research School of Engineering, CECS, The Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research School of Engineering CECS, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Research School of Engineering, CECS, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"49","issue":null,"first_page":"2654","last_page":"2658"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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":0.8001482486724854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7041372656822205},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6743341088294983},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.6245332956314087},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6078500151634216},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5469855666160583},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5156377553939819},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5113810896873474},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.45469772815704346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43733882904052734},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.43697112798690796},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.42936980724334717},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08371537923812866}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8001482486724854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7041372656822205},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6743341088294983},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6245332956314087},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6078500151634216},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5469855666160583},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5156377553939819},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5113810896873474},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.45469772815704346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43733882904052734},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.43697112798690796},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.42936980724334717},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08371537923812866},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2015.7178452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:epubs.surrey.ac.uk:840288","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/840288/","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":[{"id":"https://metadata.un.org/sdg/16","score":0.6399999856948853,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1485388545","https://openalex.org/W1487212816","https://openalex.org/W1570629387","https://openalex.org/W1924208011","https://openalex.org/W2046317813","https://openalex.org/W2070280907","https://openalex.org/W2070707809","https://openalex.org/W2085365248","https://openalex.org/W2100668143","https://openalex.org/W2106925337","https://openalex.org/W2108668360","https://openalex.org/W2118150543","https://openalex.org/W2127168030","https://openalex.org/W2137666850","https://openalex.org/W2153248083","https://openalex.org/W2155323221","https://openalex.org/W2241494097","https://openalex.org/W6629150500","https://openalex.org/W6667988988","https://openalex.org/W6690173455"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2766995619","https://openalex.org/W4224270619","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W4400595174","https://openalex.org/W2168148781","https://openalex.org/W1991848873","https://openalex.org/W2786302331"],"abstract_inverted_index":{"Binaural":[0],"localization":[1,104,124],"of":[2,61,86],"speech":[3,82,113],"sources":[4],"in":[5,46,63,123],"3-D,":[6],"using":[7],"head-related":[8],"transfer":[9],"functions":[10],"(HRTFs),":[11],"always":[12],"suffers":[13],"elevation":[14],"ambiguity":[15],"due":[16],"to":[17,72,120],"the":[18,26,39,47,81,87],"limited":[19],"high":[20],"frequency":[21],"spectral":[22],"information":[23],"available":[24],"at":[25],"receivers.":[27],"This":[28],"paper":[29],"presents":[30],"a":[31,52,64,70,95,102],"method":[32,89],"that":[33,56,118],"overcomes":[34],"this":[35,74],"limitation":[36],"by":[37,80],"exploiting":[38],"interaural":[40],"phase":[41],"and":[42,67,92,101,112],"magnitude":[43],"features":[44,62],"present":[45],"HRTF.":[48],"We":[49],"(i)":[50],"introduce":[51],"new":[53],"feature":[54,75],"vector":[55,76],"combines":[57],"these":[58],"two":[59],"sets":[60],"non-linear":[65],"fashion,":[66],"(ii)":[68],"propose":[69],"mechanism":[71],"extract":[73],"free":[77],"from":[78],"distortion":[79],"spectra.":[83],"The":[84,115],"performance":[85,125],"proposed":[88],"is":[90],"evaluated":[91],"compared":[93],"with":[94],"correlation-based":[96],"HRTF":[97],"database":[98],"matching":[99],"approach":[100],"two-step":[103],"technique":[105],"for":[106,129],"multiple":[107],"source":[108],"positions,":[109],"HRTFs":[110],"(individuals)":[111],"inputs.":[114],"results":[116],"suggest":[117],"up":[119],"20%":[121],"improvement":[122],"can":[126],"be":[127],"achieved":[128],"moderate":[130],"signal-to-noise":[131],"ratios.":[132]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
