{"id":"https://openalex.org/W2142780475","doi":"https://doi.org/10.1109/icassp.2002.5745051","title":"Audio-video array source localization for intelligent environments","display_name":"Audio-video array source localization for intelligent environments","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2142780475","doi":"https://doi.org/10.1109/icassp.2002.5745051","mag":"2142780475"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5745051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745051","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5087313939","display_name":"Kevin Wilson","orcid":"https://orcid.org/0000-0001-9141-2219"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kevin W. Wilson","raw_affiliation_strings":["Artificial Intelligence Laboratory, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA","Artificial Intelligence Laboratory, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, 02139, USA"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Laboratory, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Artificial Intelligence Laboratory, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":["Artificial Intelligence Laboratory, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA","Artificial Intelligence Laboratory, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, 02139, USA"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Laboratory, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Artificial Intelligence Laboratory, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087313939"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17681401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"II","last_page":"2109"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.8181371688842773},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8043932914733887},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6198277473449707},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6111761927604675},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5347553491592407},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5220565795898438},{"id":"https://openalex.org/keywords/stereophonic-sound","display_name":"Stereophonic sound","score":0.4250658452510834},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4218595027923584},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.41515886783599854},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35229647159576416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31967949867248535},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.30019456148147583},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2578784227371216},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.1874781847000122},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.17248660326004028},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13669165968894958}],"concepts":[{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.8181371688842773},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043932914733887},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6198277473449707},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6111761927604675},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5347553491592407},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5220565795898438},{"id":"https://openalex.org/C140631703","wikidata":"https://www.wikidata.org/wiki/Q34678","display_name":"Stereophonic sound","level":3,"score":0.4250658452510834},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4218595027923584},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.41515886783599854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35229647159576416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31967949867248535},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30019456148147583},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2578784227371216},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.1874781847000122},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.17248660326004028},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13669165968894958},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5745051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745051","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6299999952316284,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322554","display_name":"Javna Agencija za Raziskovalno Dejavnost RS","ror":"https://ror.org/059bp8k51"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1552594198","https://openalex.org/W1970763416","https://openalex.org/W2007587105","https://openalex.org/W2060108923","https://openalex.org/W2100678434","https://openalex.org/W2108461717","https://openalex.org/W2134462231"],"related_works":["https://openalex.org/W2401610501","https://openalex.org/W2098446659","https://openalex.org/W1984114325","https://openalex.org/W4253879301","https://openalex.org/W2766254947","https://openalex.org/W2126980866","https://openalex.org/W2120264472","https://openalex.org/W2185012369","https://openalex.org/W2020952589","https://openalex.org/W2903040254"],"abstract_inverted_index":{"Steerable":[0],"microphone":[1,107],"arrays":[2],"provide":[3],"a":[4,25,97,105,117,121,133],"flexible":[5],"infrastructure":[6],"for":[7,13,29],"audio":[8,67],"source":[9,126],"separation.":[10],"In":[11],"order":[12],"them":[14],"to":[15,36,74],"be":[16,24,71],"used":[17],"effectively":[18],"in":[19,27,46,96],"intelligent":[20],"environments,":[21],"there":[22],"must":[23],"mechanism":[26],"place":[28],"steering":[30,41],"the":[31,34,37,47,66,86,89],"focus":[32],"of":[33,49,88],"array":[35],"sound":[38,51],"source.":[39],"Audio-only":[40],"techniques":[42,57],"often":[43],"perform":[44],"poorly":[45],"presence":[48],"multiple":[50,101],"sources":[52],"or":[53],"strong":[54],"reverberation.":[55],"Video-only":[56],"can":[58],"achieve":[59],"high":[60],"spatial":[61],"precision":[62],"but":[63],"require":[64],"that":[65,84],"and":[68,104,132],"video":[69],"subsystems":[70],"accurately":[72],"calibrated":[73],"preserve":[75],"this":[76],"precision.":[77],"We":[78,92],"present":[79],"an":[80,112],"audio-video":[81],"localization":[82],"technique":[83,95,110],"combines":[85],"benefits":[87],"two":[90],"modalities.":[91],"implement":[93],"our":[94],"test":[98],"environment":[99],"containing":[100],"stereo":[102],"cameras":[103],"room-sized":[106],"array.":[108],"Our":[109],"achieves":[111],"8.9":[113],"dB":[114,123,135],"improvement":[115,124,136],"over":[116,125,137],"single":[118],"far-field":[119],"microphone,":[120],"6.7":[122],"separation":[127,138],"based":[128,139],"on":[129,140],"video-only":[130],"localization,":[131],"0.3":[134],"audio-only":[141],"localization.":[142]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}