{"id":"https://openalex.org/W2128334064","doi":"https://doi.org/10.1109/icmi.2002.1167026","title":"Audiovisual arrays for untethered spoken interfaces","display_name":"Audiovisual arrays for untethered spoken interfaces","publication_year":2003,"publication_date":"2003-06-26","ids":{"openalex":"https://openalex.org/W2128334064","doi":"https://doi.org/10.1109/icmi.2002.1167026","mag":"2128334064"},"language":"en","primary_location":{"id":"doi:10.1109/icmi.2002.1167026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmi.2002.1167026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. Fourth IEEE International Conference on Multimodal Interfaces","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/A5069301909","display_name":"Kevin R. Wilson","orcid":"https://orcid.org/0000-0003-0264-0872"},"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"]},{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"K. Wilson","raw_affiliation_strings":["Artificial Intelligence Laboratory, M.I.T., Cambridge, MA, USA","[Artificial Intelligence Lab., MIT, Cambridge, MA, USA]"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Laboratory, M.I.T., Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"[Artificial Intelligence Lab., MIT, Cambridge, MA, USA]","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033204574","display_name":"Vivek Rangarajan","orcid":null},"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"]},{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"V. Rangarajan","raw_affiliation_strings":["Artificial Intelligence Laboratory, M.I.T., Cambridge, MA, USA","[Artificial Intelligence Lab., MIT, Cambridge, MA, USA]"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Laboratory, M.I.T., Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"[Artificial Intelligence Lab., MIT, Cambridge, MA, USA]","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032311904","display_name":"Neal Checka","orcid":null},"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"]},{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. Checka","raw_affiliation_strings":["Artificial Intelligence Laboratory, M.I.T., Cambridge, MA, USA","[Artificial Intelligence Lab., MIT, Cambridge, MA, USA]"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Laboratory, M.I.T., Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"[Artificial Intelligence Lab., MIT, Cambridge, MA, USA]","institution_ids":["https://openalex.org/I1343180700"]}]},{"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/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"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":"T. Darrell","raw_affiliation_strings":["Artificial Intelligence Laboratory, M.I.T., Cambridge, MA, USA","[Artificial Intelligence Lab., MIT, Cambridge, MA, USA]"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Laboratory, M.I.T., Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"[Artificial Intelligence Lab., MIT, Cambridge, MA, USA]","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069301909"],"corresponding_institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.5856,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.6906682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"37","issue":null,"first_page":"389","last_page":"394"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9954000115394592,"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/microphone-array","display_name":"Microphone array","score":0.8508343696594238},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7852674126625061},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7229642271995544},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6223421096801758},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5120247006416321},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.46683230996131897},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.46530064940452576},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4465201795101166},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44494110345840454},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43994051218032837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4226198196411133},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.13801246881484985},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08664765954017639},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.07901996374130249}],"concepts":[{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.8508343696594238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852674126625061},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7229642271995544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6223421096801758},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5120247006416321},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.46683230996131897},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.46530064940452576},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4465201795101166},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44494110345840454},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43994051218032837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4226198196411133},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.13801246881484985},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08664765954017639},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.07901996374130249},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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":1,"locations":[{"id":"doi:10.1109/icmi.2002.1167026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmi.2002.1167026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. Fourth IEEE International Conference on Multimodal Interfaces","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"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":16,"referenced_works":["https://openalex.org/W1485281911","https://openalex.org/W1552594198","https://openalex.org/W1567497459","https://openalex.org/W1797158261","https://openalex.org/W1970763416","https://openalex.org/W2060108923","https://openalex.org/W2100678434","https://openalex.org/W2102858470","https://openalex.org/W2108461717","https://openalex.org/W2130607791","https://openalex.org/W2134462231","https://openalex.org/W2136559873","https://openalex.org/W2170128208","https://openalex.org/W2999617985","https://openalex.org/W3003834643","https://openalex.org/W3160125816"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W1977167953","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W107154053","https://openalex.org/W2041060376"],"abstract_inverted_index":{"When":[0],"faced":[1],"with":[2],"a":[3,7,11,14,19,31,34,89],"distant":[4],"speaker":[5,32],"at":[6],"known":[8],"location":[9,29],"in":[10,33,80],"noisy":[12],"environment,":[13],"microphone":[15,90],"array":[16,49,91],"can":[17,41],"provide":[18],"significantly":[20],"improved":[21],"audio":[22,38],"signal":[23],"for":[24,98],"speech":[25,99],"recognition.":[26],"Estimating":[27],"the":[28,73],"of":[30,50,63,75],"reverberant":[35],"environment":[36],"from":[37],"information":[39],"alone":[40],"be":[42],"quite":[43],"difficult,":[44],"so":[45],"we":[46],"use":[47],"an":[48,81],"video":[51],"cameras":[52],"to":[53,71,87,106],"aid":[54],"localization.":[55],"Stereo":[56],"processing":[57,108],"techniques":[58],"are":[59,69,85],"used":[60,86],"on":[61],"pairs":[62],"cameras,":[64],"and":[65],"foreground":[66],"3-D":[67],"points":[68],"grouped":[70],"estimate":[72],"trajectory":[74],"people":[76],"as":[77],"they":[78],"move":[79],"environment.":[82],"These":[83],"trajectories":[84],"guide":[88],"beamformer.":[92],"Initial":[93],"results":[94],"using":[95],"this":[96],"system":[97],"recognition":[100,103],"demonstrate":[101],"increased":[102],"rates":[104],"compared":[105],"non-array":[107],"techniques.":[109]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}