{"id":"https://openalex.org/W4297095267","doi":"https://doi.org/10.1109/taslp.2022.3209947","title":"Decoupled Multiple Speaker Direction-of-Arrival Estimator Under Reverberant Environments","display_name":"Decoupled Multiple Speaker Direction-of-Arrival Estimator Under Reverberant Environments","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4297095267","doi":"https://doi.org/10.1109/taslp.2022.3209947"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3209947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3209947","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":["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/A5012959870","display_name":"Yonggang Hu","orcid":"https://orcid.org/0000-0003-0414-8697"},"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":"Yonggang Hu","raw_affiliation_strings":["Research School of Engineering, Australian National University, Canberra, A.C.T., Australia"],"raw_orcid":"https://orcid.org/0000-0003-0414-8697","affiliations":[{"raw_affiliation_string":"Research School of Engineering, Australian National University, Canberra, A.C.T., Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058898992","display_name":"Prasanga N. Samarasinghe","orcid":"https://orcid.org/0000-0002-5589-4203"},"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":"Prasanga N. Samarasinghe","raw_affiliation_strings":["Research School of Engineering, Australian National University, Canberra, A.C.T., Australia"],"raw_orcid":"https://orcid.org/0000-0002-5589-4203","affiliations":[{"raw_affiliation_string":"Research School of Engineering, Australian National University, Canberra, A.C.T., Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001052072","display_name":"Sharon Gannot","orcid":"https://orcid.org/0000-0002-2885-170X"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sharon Gannot","raw_affiliation_strings":["Faculty of Engineering, Bar-Ilan University, Ramat-Gan, Israel"],"raw_orcid":"https://orcid.org/0000-0002-2885-170X","affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"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, Australian National University, Canberra, A.C.T., Australia"],"raw_orcid":"https://orcid.org/0000-0001-6937-7218","affiliations":[{"raw_affiliation_string":"Research School of Engineering, Australian National University, Canberra, A.C.T., Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6757,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90537724,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"3120","last_page":"3133"},"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":0.9976999759674072,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/reverberation","display_name":"Reverberation","score":0.7516483068466187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6653921008110046},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6467110514640808},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.6375441551208496},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.5550572276115417},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5396625399589539},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5339734554290771},{"id":"https://openalex.org/keywords/bin","display_name":"Bin","score":0.5219261646270752},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.41002246737480164},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.39337068796157837},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3667600452899933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3279244899749756},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2394341230392456},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19823691248893738},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1047220230102539},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09680375456809998},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.07612630724906921}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7516483068466187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6653921008110046},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6467110514640808},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.6375441551208496},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.5550572276115417},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5396625399589539},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5339734554290771},{"id":"https://openalex.org/C156273044","wikidata":"https://www.wikidata.org/wiki/Q4913766","display_name":"Bin","level":2,"score":0.5219261646270752},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.41002246737480164},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.39337068796157837},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3667600452899933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3279244899749756},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2394341230392456},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19823691248893738},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1047220230102539},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09680375456809998},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.07612630724906921},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"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/taslp.2022.3209947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3209947","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1811954879","https://openalex.org/W1907050691","https://openalex.org/W1966081805","https://openalex.org/W1987906574","https://openalex.org/W2003564384","https://openalex.org/W2011430131","https://openalex.org/W2098795429","https://openalex.org/W2104617572","https://openalex.org/W2110403504","https://openalex.org/W2113638573","https://openalex.org/W2117678320","https://openalex.org/W2128131274","https://openalex.org/W2128970593","https://openalex.org/W2129501075","https://openalex.org/W2130423769","https://openalex.org/W2139159265","https://openalex.org/W2144923884","https://openalex.org/W2151582818","https://openalex.org/W2152632507","https://openalex.org/W2156507391","https://openalex.org/W2162607306","https://openalex.org/W2168299838","https://openalex.org/W2173466987","https://openalex.org/W2213904342","https://openalex.org/W2231821870","https://openalex.org/W2514127661","https://openalex.org/W2538968649","https://openalex.org/W2552290276","https://openalex.org/W2568308529","https://openalex.org/W2744375432","https://openalex.org/W2745195618","https://openalex.org/W2784289299","https://openalex.org/W2804325970","https://openalex.org/W2810934215","https://openalex.org/W2885219692","https://openalex.org/W2890094769","https://openalex.org/W2899638354","https://openalex.org/W2903697385","https://openalex.org/W2917254586","https://openalex.org/W2917804342","https://openalex.org/W2939592795","https://openalex.org/W2939669751","https://openalex.org/W2939743271","https://openalex.org/W2964208065","https://openalex.org/W2973167466","https://openalex.org/W2985838805","https://openalex.org/W2994698073","https://openalex.org/W2997721189","https://openalex.org/W2997989584","https://openalex.org/W3011890046","https://openalex.org/W3015758669","https://openalex.org/W3021261768","https://openalex.org/W3092632462","https://openalex.org/W3094665499","https://openalex.org/W3100336094","https://openalex.org/W3100987222","https://openalex.org/W3101115403","https://openalex.org/W3102937397","https://openalex.org/W3105563130","https://openalex.org/W3107276689","https://openalex.org/W3115376274","https://openalex.org/W3115508264","https://openalex.org/W3129910207","https://openalex.org/W3157787880","https://openalex.org/W3162934980","https://openalex.org/W3197097128","https://openalex.org/W4224933823","https://openalex.org/W6639805832"],"related_works":["https://openalex.org/W2107701374","https://openalex.org/W2950072893","https://openalex.org/W1616588898","https://openalex.org/W4249504934","https://openalex.org/W2009811519","https://openalex.org/W4225639054","https://openalex.org/W4200633555","https://openalex.org/W1967434260","https://openalex.org/W2115073044","https://openalex.org/W4313577963"],"abstract_inverted_index":{"Direction-of-arrival":[0],"(DOA)":[1],"estimation":[2,141],"for":[3],"multiple":[4],"simultaneous":[5],"speakers":[6,151],"in":[7,17,60,69,194],"reverberant":[8,171],"environments":[9,207],"is":[10,76],"still":[11],"one":[12],"of":[13,125,150],"the":[14,18,48,57,61,70,74,89,107,148,158,174,186],"challenging":[15],"tasks":[16],"audio":[19],"signal":[20],"processing":[21],"field.":[22],"A":[23],"recent":[24],"approach":[25],"addresses":[26],"this":[27,54,95],"problem":[28],"using":[29,142,166],"a":[30,44,99,133,209],"spherical":[31],"harmonics":[32],"domain":[33],"feature":[34],"named":[35],"<italic":[36],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[37,215],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">relative":[38],"harmonic":[39],"coefficients</i>":[40],"(RHC).":[41],"Based":[42],"on":[43,157],"bin-wise":[45],"operation":[46],"across":[47],"STFT":[49,81,163],"(short-time":[50],"Fourier":[51],"transform)":[52],"domain,":[53],"method":[55,75,192],"detects":[56],"direct-path":[58,135,161],"RHC":[59,136],"first":[62],"stage,":[63],"followed":[64],"by":[65],"single":[66],"source":[67],"localization":[68,122,182],"second":[71],"stage.":[72],"However,":[73],"computationally":[77,102],"expensive":[78],"as":[79],"each":[80],"bin":[82],"requires":[83],"an":[84,195],"exhaustive":[85],"grid":[86],"search":[87,112],"over":[88],"two-dimensional":[90],"(2-D)":[91],"directional":[92],"space.":[93],"In":[94],"paper,":[96],"we":[97],"propose":[98],"significantly":[100],"more":[101],"efficient":[103],"alternative":[104],"that":[105],"decouples":[106],"azimuth":[108],"and":[109,138,145,152,169],"elevation":[110],"2-D":[111],"to":[113,185,200],"two":[114,126],"separate":[115],"one-dimensional":[116],"(1-D)":[117],"search.":[118],"The":[119],"proposed":[120,191],"multi-speaker":[121],"algorithm":[123],"comprises":[124],"main":[127],"steps,":[128],"responsible":[129],"for:":[130],"(i)":[131],"achieving":[132,180],"joint":[134],"detection":[137],"decoupled":[139],"DOA":[140],"1-D":[143],"search;":[144],"(ii)":[146],"counting":[147],"number":[149],"estimating":[153],"their":[154],"DOAs":[155],"based":[156],"estimates":[159],"from":[160],"dominated":[162],"bins.":[164],"Experiments":[165],"both":[167],"simulated":[168],"real-life":[170],"recordings":[172],"confirm":[173],"significant":[175],"computational":[176],"complexity":[177],"reduction":[178],"while":[179],"competitive":[181],"accuracy,":[183],"compared":[184],"baseline":[187],"approaches.":[188],"Although":[189],"our":[190],"performs":[193],"unsupervised":[196],"manner,":[197],"it":[198],"proves":[199],"be":[201],"applicable":[202],"even":[203],"under":[204],"unfavorable":[205],"acoustic":[206],"with":[208],"high":[210],"reverberation":[211],"level":[212],"(e.g.,":[213],"<inline-formula":[214],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[216],"notation=\"LaTeX\">$T_{60}=1$</tex-math></inline-formula>":[217],"second).":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}