{"id":"https://openalex.org/W2933484427","doi":"https://doi.org/10.1109/icassp40776.2020.9053825","title":"Static Visual Spatial Priors for DoA Estimation","display_name":"Static Visual Spatial Priors for DoA Estimation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2933484427","doi":"https://doi.org/10.1109/icassp40776.2020.9053825","mag":"2933484427"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.00202","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084169592","display_name":"Pawe\u0142 \u015awi\u0119toja\u0144ski","orcid":"https://orcid.org/0000-0001-5896-4505"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Pawel Swietojanski","raw_affiliation_strings":["University of New South Wales, Sydney, Australia","University of New South Wales,#TAB#"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"University of New South Wales,#TAB#","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101805095","display_name":"Ondrej Miksik","orcid":"https://orcid.org/0000-0001-8528-2956"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ondrej Miksik","raw_affiliation_strings":["Microsoft","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084169592"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00477592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 1604 289","issue":null,"first_page":"4935","last_page":"4939"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9937999844551086,"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/computer-science","display_name":"Computer science","score":0.7859116792678833},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6016212105751038},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5563668608665466},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.5327019691467285},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.45856985449790955},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.44278332591056824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4399257004261017},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4296721816062927},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.425632506608963},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4143303632736206},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.2276887595653534},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16388285160064697},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11060568690299988},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07706624269485474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7859116792678833},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6016212105751038},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5563668608665466},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.5327019691467285},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.45856985449790955},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.44278332591056824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4399257004261017},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4296721816062927},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.425632506608963},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4143303632736206},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2276887595653534},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16388285160064697},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11060568690299988},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07706624269485474},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.00202","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.00202","pdf_url":"https://arxiv.org/pdf/1904.00202","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2933484427","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.00202v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1904.00202","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.00202","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/ppdj-v169","is_oa":true,"landing_page_url":"https://doi.org/10.17023/ppdj-v169","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.00202","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.00202","pdf_url":"https://arxiv.org/pdf/1904.00202","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2933484427.pdf"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W97351935","https://openalex.org/W126779258","https://openalex.org/W653761051","https://openalex.org/W1233635381","https://openalex.org/W1494198834","https://openalex.org/W1589387574","https://openalex.org/W1861492603","https://openalex.org/W1971618559","https://openalex.org/W1988699227","https://openalex.org/W2024139303","https://openalex.org/W2033819227","https://openalex.org/W2033979122","https://openalex.org/W2045587041","https://openalex.org/W2046317813","https://openalex.org/W2054389289","https://openalex.org/W2074142487","https://openalex.org/W2101658087","https://openalex.org/W2113638573","https://openalex.org/W2113940248","https://openalex.org/W2114863372","https://openalex.org/W2124592697","https://openalex.org/W2126060993","https://openalex.org/W2129866629","https://openalex.org/W2131090450","https://openalex.org/W2138203286","https://openalex.org/W2148613904","https://openalex.org/W2155208493","https://openalex.org/W2157431481","https://openalex.org/W2158541895","https://openalex.org/W2160783189","https://openalex.org/W2167362547","https://openalex.org/W2167687475","https://openalex.org/W2219249508","https://openalex.org/W2328078142","https://openalex.org/W2340897893","https://openalex.org/W2461677039","https://openalex.org/W2587662404","https://openalex.org/W2605418763","https://openalex.org/W2672714283","https://openalex.org/W2737258237","https://openalex.org/W2763188033","https://openalex.org/W2794549886","https://openalex.org/W2809543295","https://openalex.org/W2928160594","https://openalex.org/W2963840672","https://openalex.org/W2963881378","https://openalex.org/W2964342924","https://openalex.org/W4232280717","https://openalex.org/W6605165268","https://openalex.org/W6628170318","https://openalex.org/W6629717138","https://openalex.org/W6639102338","https://openalex.org/W6677010908","https://openalex.org/W6679687845","https://openalex.org/W6688816777","https://openalex.org/W6696085341","https://openalex.org/W6701573534","https://openalex.org/W6749858761"],"related_works":["https://openalex.org/W3015955821","https://openalex.org/W2267737560","https://openalex.org/W837791456","https://openalex.org/W67981183","https://openalex.org/W2767365152","https://openalex.org/W3107350173","https://openalex.org/W3007298809","https://openalex.org/W2952390294","https://openalex.org/W3167221503","https://openalex.org/W2952038832","https://openalex.org/W3209103740","https://openalex.org/W3045355015","https://openalex.org/W3126672009","https://openalex.org/W2116478388","https://openalex.org/W3099966603","https://openalex.org/W2585430211","https://openalex.org/W3030188676","https://openalex.org/W2944059049","https://openalex.org/W639018713","https://openalex.org/W2942730777"],"abstract_inverted_index":{"As":[0],"we":[1,9,22,37,107],"interact":[2],"with":[3,11],"the":[4,25,86,98,114,134,140],"world,":[5],"for":[6,42,49],"example":[7],"when":[8,75],"communicate":[10],"our":[12,111,146,157],"colleagues":[13],"in":[14,29,68],"a":[15,46,101,149],"large":[16],"open":[17],"space":[18],"or":[19,52],"meeting":[20],"room,":[21],"continuously":[23],"analyse":[24],"surrounding":[26],"environment":[27,135],"and,":[28],"particular,":[30],"localise":[31],"and":[32,95,154],"recognise":[33],"acoustic":[34],"events.":[35],"While":[36],"largely":[38],"take":[39,90],"such":[40,73],"abilities":[41],"granted,":[43],"they":[44,57],"represent":[45],"challenging":[47],"problem":[48],"current":[50],"robots":[51],"smart":[53],"voice":[54],"assistants":[55],"as":[56],"can":[58],"be":[59],"easily":[60],"fooled":[61],"by":[62],"high":[63],"degree":[64],"of":[65,118,121,139],"sound":[66],"interference":[67],"acoustically":[69],"complex":[70],"environments.":[71],"Preventing":[72],"failures":[74],"using":[76],"solely":[77],"audio":[78],"data":[79],"is":[80,113],"challenging,":[81],"if":[82],"not":[83],"impossible":[84],"since":[85],"algorithms":[87],"need":[88],"to":[89,110,136],"into":[91],"account":[92],"wider":[93],"context":[94],"often":[96],"understand":[97],"scene":[99],"on":[100,148],"semantic":[102],"level.":[103],"In":[104],"this":[105],"paper,":[106],"propose":[108],"what":[109],"knowledge":[112],"first":[115],"multi-modal":[116],"direction":[117],"arrival":[119],"(DoA)":[120],"sound,":[122],"which":[123],"uses":[124],"static":[125],"visual":[126],"spatial":[127],"prior":[128],"providing":[129],"an":[130],"auxiliary":[131],"information":[132],"about":[133],"suppress":[137],"some":[138],"false":[141],"DoA":[142,163],"detections.":[143],"We":[144],"validate":[145],"approach":[147,158],"newly":[150],"collected":[151],"real-world":[152],"dataset,":[153],"show":[155],"that":[156],"consistently":[159],"improves":[160],"over":[161],"classic":[162],"baselines.":[164]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}