{"id":"https://openalex.org/W4392904318","doi":"https://doi.org/10.1109/icassp48485.2024.10447883","title":"Robust DoA Estimation from Deep Acoustic Imaging","display_name":"Robust DoA Estimation from Deep Acoustic Imaging","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904318","doi":"https://doi.org/10.1109/icassp48485.2024.10447883"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5081976456","display_name":"Adrian S. Roman","orcid":null},"institutions":[{"id":"https://openalex.org/I144571360","display_name":"Viterbo University","ror":"https://ror.org/039p8pn96","country_code":"US","type":"education","lineage":["https://openalex.org/I144571360"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Adrian S. Roman","raw_affiliation_strings":["University of Southern California,Viterbi School of Engineering,California,USA","Viterbi School of Engineering, University of Southern California, California, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Viterbi School of Engineering,California,USA","institution_ids":["https://openalex.org/I144571360","https://openalex.org/I1174212"]},{"raw_affiliation_string":"Viterbi School of Engineering, University of Southern California, California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027526258","display_name":"Iran R. Roman","orcid":"https://orcid.org/0000-0003-3781-7244"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iran R. Roman","raw_affiliation_strings":["New York University,Music and Audio Research Laboratory,New York,USA","Music and Audio Research Laboratory, New York University, New York, USA"],"affiliations":[{"raw_affiliation_string":"New York University,Music and Audio Research Laboratory,New York,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University, New York, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031398497","display_name":"Juan Pablo Bello","orcid":"https://orcid.org/0000-0001-8561-5204"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan P. Bello","raw_affiliation_strings":["New York University,Music and Audio Research Laboratory,New York,USA","Music and Audio Research Laboratory, New York University, New York, USA"],"affiliations":[{"raw_affiliation_string":"New York University,Music and Audio Research Laboratory,New York,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University, New York, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081976456"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I144571360"],"apc_list":null,"apc_paid":null,"fwci":2.0174,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8642649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1321","last_page":"1325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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/T11008","display_name":"Aerodynamics and Acoustics in Jet Flows","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11698","display_name":"Underwater Acoustics Research","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ambisonics","display_name":"Ambisonics","score":0.8110964298248291},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7173478603363037},{"id":"https://openalex.org/keywords/azimuth","display_name":"Azimuth","score":0.6984829306602478},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6938729882240295},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6242280006408691},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5924423336982727},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4587644934654236},{"id":"https://openalex.org/keywords/superresolution","display_name":"Superresolution","score":0.42655906081199646},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4229309856891632},{"id":"https://openalex.org/keywords/image-resolution","display_name":"Image resolution","score":0.41781607270240784},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.413674920797348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3634182810783386},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.33901357650756836},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2742794156074524},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.15804776549339294},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.1330164670944214},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10508373379707336},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.092924565076828},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08997350931167603}],"concepts":[{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.8110964298248291},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7173478603363037},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.6984829306602478},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6938729882240295},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6242280006408691},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5924423336982727},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4587644934654236},{"id":"https://openalex.org/C141239990","wikidata":"https://www.wikidata.org/wiki/Q957423","display_name":"Superresolution","level":3,"score":0.42655906081199646},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4229309856891632},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.41781607270240784},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.413674920797348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3634182810783386},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.33901357650756836},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2742794156074524},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.15804776549339294},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.1330164670944214},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10508373379707336},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.092924565076828},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08997350931167603},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/102548","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/102548","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6205568849","display_name":"III: Medium: Spatial Sound Scene Description","funder_award_id":"1955357","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1910115052","https://openalex.org/W1970571676","https://openalex.org/W2494085323","https://openalex.org/W2810934215","https://openalex.org/W2888793942","https://openalex.org/W2899595090","https://openalex.org/W2963729050","https://openalex.org/W2970746371","https://openalex.org/W2982341288","https://openalex.org/W3083274258","https://openalex.org/W3117314925","https://openalex.org/W3197097128","https://openalex.org/W3206329344","https://openalex.org/W3210404408","https://openalex.org/W4205689591","https://openalex.org/W4221141618","https://openalex.org/W4307481987","https://openalex.org/W4324116353","https://openalex.org/W4380994299","https://openalex.org/W4392904420","https://openalex.org/W4393782081","https://openalex.org/W4394641766","https://openalex.org/W6677645113","https://openalex.org/W6767784004"],"related_works":["https://openalex.org/W2897160306","https://openalex.org/W2604047122","https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W4387872666","https://openalex.org/W2487629029"],"abstract_inverted_index":{"Direction":[0],"of":[1,108],"arrival":[2],"estimation":[3,94],"(DoAE)":[4],"aims":[5],"at":[6],"tracking":[7],"a":[8,31,67,87,97,100],"sound":[9],"in":[10,30],"azimuth":[11],"and":[12,95,99],"elevation.":[13],"Recent":[14],"advancements":[15],"include":[16],"data-driven":[17],"models":[18,78],"with":[19],"inputs":[20],"derived":[21],"from":[22,52],"ambisonics":[23],"intensity":[24,36],"vectors":[25],"or":[26,39],"correlations":[27],"between":[28],"channels":[29],"microphone":[32,54],"array.":[33],"A":[34],"spherical":[35],"map":[37],"(SIM),":[38],"acoustic":[40,109],"image,":[41],"is":[42],"an":[43],"alternative":[44],"input":[45],"representation":[46],"that":[47,79,89],"remains":[48],"underexplored.":[49],"SIMs":[50,81,91],"benefit":[51],"high-resolution":[53],"arrays,":[55],"yet":[56],"most":[57],"DoAE":[58,77,93,112],"datasets":[59],"use":[60,80],"low-resolution":[61,72],"ones.":[62],"Therefore,":[63],"we":[64,75],"first":[65],"propose":[66],"super-resolution":[68],"method":[69],"to":[70,86],"upsample":[71],"microphones.":[73],"Next,":[74],"benchmark":[76],"as":[82],"input.":[83],"We":[84],"arrive":[85],"model":[88],"uses":[90],"for":[92,111],"outperforms":[96],"baseline":[98],"state-of-the-art":[101],"model.":[102],"Our":[103],"study":[104],"highlights":[105],"the":[106],"relevance":[107],"imaging":[110],"tasks.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}