{"id":"https://openalex.org/W1819839966","doi":"https://doi.org/10.1109/icassp.2015.7178010","title":"A joint audio-visual approach to audio localization","display_name":"A joint audio-visual approach to audio localization","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1819839966","doi":"https://doi.org/10.1109/icassp.2015.7178010","mag":"1819839966"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178010","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/ws/files/218588467/Jensen.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041263382","display_name":"Jesper Rindom Jensen","orcid":"https://orcid.org/0000-0001-6023-8270"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Rindom Jensen","raw_affiliation_strings":["Audio Analysis Lab, AD:MT, Aalborg University, Denmark","[Audio Analysis Lab, AD:MT Aalborg University, Denmark]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Analysis Lab, AD:MT, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"[Audio Analysis Lab, AD:MT Aalborg University, Denmark]","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026658144","display_name":"Mads Gr\u00e6sb\u00f8ll Christensen","orcid":"https://orcid.org/0000-0003-3586-7969"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mads Graesboll Christensen","raw_affiliation_strings":["Audio Analysis Lab, AD:MT, Aalborg University, Denmark","[Audio Analysis Lab, AD:MT Aalborg University, Denmark]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Analysis Lab, AD:MT, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"[Audio Analysis Lab, AD:MT Aalborg University, Denmark]","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05026166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":null,"first_page":"454","last_page":"458"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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":0.9909999966621399,"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/audio-visual","display_name":"Audio visual","score":0.7869632244110107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7400956749916077},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6989767551422119},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.46833324432373047},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4282224178314209},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.41521769762039185},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4017215073108673},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3047627806663513},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2961343824863434},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07952505350112915}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7869632244110107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7400956749916077},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6989767551422119},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.46833324432373047},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4282224178314209},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.41521769762039185},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4017215073108673},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3047627806663513},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2961343824863434},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07952505350112915},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2015.7178010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178010","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:pure.atira.dk:publications/bcbfeeaa-6ec7-4733-af11-ed9df8dc34ae","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/bcbfeeaa-6ec7-4733-af11-ed9df8dc34ae","pdf_url":"https://vbn.aau.dk/ws/files/218588467/Jensen.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jensen, J R & Christensen, M G 2015, 'A Joint Audio-Visual Approach to Audio Localization', I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings, pp. 454-458. https://doi.org/10.1109/ICASSP.2015.7178010","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/bcbfeeaa-6ec7-4733-af11-ed9df8dc34ae","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/bcbfeeaa-6ec7-4733-af11-ed9df8dc34ae","pdf_url":"https://vbn.aau.dk/ws/files/218588467/Jensen.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jensen, J R & Christensen, M G 2015, 'A Joint Audio-Visual Approach to Audio Localization', I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings, pp. 454-458. https://doi.org/10.1109/ICASSP.2015.7178010","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1846844445","display_name":null,"funder_award_id":"1337-00084","funder_id":"https://openalex.org/F4320322928","funder_display_name":"Danmarks Frie Forskningsfond"},{"id":"https://openalex.org/G7844739465","display_name":null,"funder_award_id":"DFF 1337-00084","funder_id":"https://openalex.org/F4320322928","funder_display_name":"Danmarks Frie Forskningsfond"}],"funders":[{"id":"https://openalex.org/F4320322928","display_name":"Danmarks Frie Forskningsfond","ror":"https://ror.org/02sptwz63"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1819839966.pdf","grobid_xml":"https://content.openalex.org/works/W1819839966.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W250076511","https://openalex.org/W1525535255","https://openalex.org/W1965392255","https://openalex.org/W1975481660","https://openalex.org/W1989471337","https://openalex.org/W2005583431","https://openalex.org/W2009391653","https://openalex.org/W2011594914","https://openalex.org/W2029210671","https://openalex.org/W2049179961","https://openalex.org/W2071608040","https://openalex.org/W2074086498","https://openalex.org/W2106557043","https://openalex.org/W2114431062","https://openalex.org/W2129227482","https://openalex.org/W2131573133","https://openalex.org/W2142612029","https://openalex.org/W2149460029","https://openalex.org/W2154332337","https://openalex.org/W2154496665","https://openalex.org/W2157775762","https://openalex.org/W2160339379","https://openalex.org/W2164809687","https://openalex.org/W2167206042","https://openalex.org/W2169770604","https://openalex.org/W2172485033","https://openalex.org/W2290091680","https://openalex.org/W2402482292","https://openalex.org/W2570759978","https://openalex.org/W3149794337","https://openalex.org/W6651850059","https://openalex.org/W6696558644","https://openalex.org/W6712694631"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W4252830433","https://openalex.org/W4214771044","https://openalex.org/W4382560817","https://openalex.org/W4387698063","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W1611900921","https://openalex.org/W3110605476"],"abstract_inverted_index":{"Localization":[0],"of":[1,124],"audio":[2,106],"sources":[3],"is":[4,31,119],"an":[5,95],"important":[6],"research":[7],"problem,":[8],"e.g.,":[9,88],"to":[10,32,49],"facilitate":[11],"noise":[12],"reduction.":[13],"In":[14,52],"the":[15,18,46,55,62,69,126],"recent":[16],"years,":[17],"problem":[19],"has":[20],"been":[21],"tackled":[22],"using":[23,89,125],"distributed":[24],"microphone":[25],"arrays":[26],"(DMA).":[27],"A":[28],"common":[29],"approach":[30],"apply":[33],"direction-of-arrival":[34],"(DOA)":[35],"estimation":[36,64],"on":[37,110],"each":[38,86],"array":[39],"(denoted":[40],"as":[41],"nodes),":[42],"and":[43,83,102,113],"then":[44],"map":[45],"DOA":[47,63,101],"estimates":[48,79],"a":[50,74,120],"location.":[51],"practice,":[53],"however,":[54],"individual":[56],"nodes":[57],"contain":[58],"few":[59],"microphones,":[60],"limiting":[61],"accuracy":[65],"and,":[66],"thereby,":[67],"also":[68,81],"localization":[70,129],"performance.":[71],"We":[72],"investigate":[73],"new":[75],"approach,":[76],"where":[77],"range":[78,103],"are":[80],"obtained":[82],"utilized":[84],"from":[85],"node,":[87],"time-of-flight":[90],"cameras.":[91],"Moreover,":[92],"we":[93],"propose":[94],"optimal":[96],"method":[97],"for":[98,105],"weighting":[99],"such":[100],"information":[104],"localization.":[107],"Our":[108],"experiments":[109],"both":[111],"synthetic":[112],"real":[114],"data":[115],"show":[116],"that":[117],"there":[118],"clear,":[121],"potential":[122],"advantage":[123],"joint":[127],"audio-visual":[128],"framework.":[130]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}