{"id":"https://openalex.org/W2163141813","doi":"https://doi.org/10.1109/icassp.2004.1327252","title":"Multiple person and speaker activity tracking with a particle filter","display_name":"Multiple person and speaker activity tracking with a particle filter","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2163141813","doi":"https://doi.org/10.1109/icassp.2004.1327252","mag":"2163141813"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1327252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1327252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 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/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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"N. Checka","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023061955","display_name":"Kirk Wilson","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K.W. Wilson","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069218584","display_name":"Michael R. Siracusa","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M.R. Siracusa","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, 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":"T. Darrell","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032311904"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":6.5709,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.97346981,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"5","issue":null,"first_page":"V","last_page":"881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9961000084877014,"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/particle-filter","display_name":"Particle filter","score":0.7924026250839233},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.629446804523468},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6069499254226685},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46144595742225647},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4157163202762604},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.26089173555374146},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08948695659637451}],"concepts":[{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.7924026250839233},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.629446804523468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6069499254226685},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46144595742225647},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4157163202762604},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26089173555374146},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08948695659637451},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1327252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1327252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1513768190","https://openalex.org/W1524095503","https://openalex.org/W1556691776","https://openalex.org/W1648602279","https://openalex.org/W1984630900","https://openalex.org/W2088804976","https://openalex.org/W2108248087","https://openalex.org/W2117082318","https://openalex.org/W2142511364","https://openalex.org/W2161406034","https://openalex.org/W2168573944","https://openalex.org/W3140992804","https://openalex.org/W6630587866","https://openalex.org/W6631290298","https://openalex.org/W6633265401","https://openalex.org/W6677452075"],"related_works":["https://openalex.org/W1989212443","https://openalex.org/W2103644279","https://openalex.org/W4302986566","https://openalex.org/W1968585197","https://openalex.org/W2135362996","https://openalex.org/W2150578674","https://openalex.org/W877199042","https://openalex.org/W2122155275","https://openalex.org/W4247544095","https://openalex.org/W2535707089"],"abstract_inverted_index":{"In":[0,16],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,17,26,32,96],"system":[6,86],"that":[7,84],"combines":[8],"sound":[9],"and":[10,37,41,50,63,78,92],"vision":[11],"to":[12],"track":[13,89],"multiple":[14],"people.":[15,100],"cluttered":[18],"or":[19],"noisy":[20],"scene,":[21],"multi-person":[22],"tracking":[23],"estimates":[24],"have":[25],"distinctly":[27],"non-Gaussian":[28],"distribution.":[29],"We":[30,69],"apply":[31],"particle":[33],"filter":[34],"with":[35,75],"audio":[36,49],"video":[38,51],"state":[39,54],"components,":[40],"derive":[42],"observation":[43],"likelihood":[44],"methods":[45],"based":[46],"on":[47],"both":[48],"measurements.":[52],"Our":[53,81],"includes":[55],"the":[56,90],"number":[57,98],"of":[58,95,99],"people":[59],"present,":[60],"their":[61],"positions,":[62],"whether":[64],"each":[65],"person":[66],"is":[67],"talking.":[68],"show":[70,83],"experiments":[71],"in":[72],"an":[73],"environment":[74],"sparse":[76],"microphones":[77],"monocular":[79],"cameras.":[80],"results":[82],"our":[85],"can":[87],"accurately":[88],"locations":[91],"speech":[93],"activity":[94],"varying":[97]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
