{"id":"https://openalex.org/W4416798424","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249410","title":"Neural Network-Assisted Joint DOA Estimation and Beamforming with First-Order Reflection Modeling","display_name":"Neural Network-Assisted Joint DOA Estimation and Beamforming with First-Order Reflection Modeling","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798424","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249410"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5106698171","display_name":"Yichen Yang","orcid":"https://orcid.org/0009-0007-4812-1900"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichen Yang","raw_affiliation_strings":["Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028806892","display_name":"Chao Pan","orcid":"https://orcid.org/0000-0002-1214-041X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Pan","raw_affiliation_strings":["Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061099115","display_name":"Qiang Gao","orcid":"https://orcid.org/0000-0003-2929-4623"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Gao","raw_affiliation_strings":["Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071376063","display_name":"Jacob Benesty","orcid":"https://orcid.org/0000-0002-0036-5865"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]},{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jacob Benesty","raw_affiliation_strings":["University of Quebec,INRS-EMT,Montreal,QC,Canada,H5A 1K6"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Quebec,INRS-EMT,Montreal,QC,Canada,H5A 1K6","institution_ids":["https://openalex.org/I159129438","https://openalex.org/I39481719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075702573","display_name":"Shoji Makino","orcid":"https://orcid.org/0000-0003-1934-640X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoji Makino","raw_affiliation_strings":["Graduate School of Information, Production and Systems, Waseda University,Kitakyushu,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information, Production and Systems, Waseda University,Kitakyushu,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056129529","display_name":"Jingdong Chen","orcid":"https://orcid.org/0000-0003-0083-9247"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingdong Chen","raw_affiliation_strings":["Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Center of Intelligent Acoustics and Immersive Communications,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.064,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8264538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9376999735832214,"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":0.9376999735832214,"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/T10931","display_name":"Direction-of-Arrival Estimation Techniques","score":0.048900000751018524,"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":0.002899999963119626,"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/microphone-array","display_name":"Microphone array","score":0.6164000034332275},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5412999987602234},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5138999819755554},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5109000205993652},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.4977000057697296},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4934000074863434},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4733000099658966},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4569999873638153},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.4494999945163727},{"id":"https://openalex.org/keywords/independent-component-analysis","display_name":"Independent component analysis","score":0.41929998993873596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7239999771118164},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6164000034332275},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5412999987602234},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5138999819755554},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5109000205993652},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.4977000057697296},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4781999886035919},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4733000099658966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4569999873638153},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.4494999945163727},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4228000044822693},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40849998593330383},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.3930000066757202},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3582000136375427},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.34709998965263367},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3384000062942505},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C121475858","wikidata":"https://www.wikidata.org/wiki/Q2735911","display_name":"Spatial filter","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G104371776","display_name":null,"funder_award_id":"2024YFF0505502","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5889320198","display_name":null,"funder_award_id":"62171373,61831019,62192713","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W653761051","https://openalex.org/W1484863014","https://openalex.org/W1552314771","https://openalex.org/W1993294423","https://openalex.org/W2005602327","https://openalex.org/W2030486566","https://openalex.org/W2040782121","https://openalex.org/W2068463586","https://openalex.org/W2094287371","https://openalex.org/W2111320049","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2171355909","https://openalex.org/W2221409856","https://openalex.org/W2295905273","https://openalex.org/W2384242984","https://openalex.org/W2398042854","https://openalex.org/W2517616541","https://openalex.org/W2767831780","https://openalex.org/W3004309045","https://openalex.org/W3123199376","https://openalex.org/W3160140981","https://openalex.org/W3162341667","https://openalex.org/W3196940724","https://openalex.org/W3206110053","https://openalex.org/W3215836504","https://openalex.org/W4210849719","https://openalex.org/W4285116935","https://openalex.org/W4295832084","https://openalex.org/W4388820300","https://openalex.org/W4391621214","https://openalex.org/W4400275345","https://openalex.org/W4403674731"],"related_works":[],"abstract_inverted_index":{"Source":[0],"signal":[1,13],"extraction":[2,36],"and":[3,71,90,146],"direction-of-arrival":[4],"(DOA)":[5],"estimation":[6,24,148],"are":[7],"core":[8],"tasks":[9],"in":[10,20,44,105,150],"microphone":[11],"array":[12],"processing.":[14],"However,":[15],"their":[16],"performance":[17],"degrades":[18],"significantly":[19,141],"reverberant":[21,151],"environments:":[22],"DOA":[23,89,147],"struggles":[25],"to":[26,38,67,85,128],"distinguish":[27],"the":[28,41,54,68,72,77,88,91,131,138],"direct":[29,69],"path":[30,70],"from":[31,76],"strong":[32],"reflections,":[33],"while":[34],"source":[35,55,115],"fails":[37],"effectively":[39],"exploit":[40],"spatial":[42],"cues":[43],"early":[45],"reflections.":[46],"This":[47],"paper":[48],"proposes":[49],"a":[50,60,106,120],"novel":[51],"formulation":[52],"of":[53,63,94],"array-manifold":[56],"vector":[57],"(AMV)":[58],"as":[59],"linear":[61],"combination":[62,92],"free-field":[64],"AMVs":[65],"corresponding":[66],"four":[73],"first-order":[74],"reflections":[75],"surrounding":[78],"walls.":[79],"A":[80],"neural":[81],"network":[82],"is":[83,102],"developed":[84],"jointly":[86],"estimate":[87],"weights":[93],"these":[95],"component":[96],"AMVs.":[97],"The":[98],"resulting":[99],"composite":[100],"AMV":[101],"then":[103],"used":[104],"minimum":[107],"variance":[108],"distortionless":[109],"response":[110],"(MVDR)":[111],"beamformer":[112],"for":[113],"enhanced":[114],"extraction.":[116],"Additionally,":[117],"we":[118],"introduce":[119],"location-based":[121],"training":[122],"strategy":[123],"that":[124,137],"enables":[125],"end-to-end":[126],"learning":[127],"automatically":[129],"identify":[130],"direct-path":[132],"direction.":[133],"Simulation":[134],"results":[135],"show":[136],"proposed":[139],"method":[140],"improves":[142],"both":[143],"speech":[144],"quality":[145],"accuracy":[149],"environments.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}