{"id":"https://openalex.org/W2074074031","doi":"https://doi.org/10.1109/icassp.2002.5745023","title":"A self-calibrating algorithm for speaker tracking based on audio-visual statistical models","display_name":"A self-calibrating algorithm for speaker tracking based on audio-visual statistical models","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2074074031","doi":"https://doi.org/10.1109/icassp.2002.5745023","mag":"2074074031"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5745023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745023","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/A5111941455","display_name":"Matthew J. Beal","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210115172","display_name":"Oxford Centre for Computational Neuroscience","ror":"https://ror.org/026ejyb70","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I4210115172"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Matthew J. Beal","raw_affiliation_strings":["Gatsby Computational Neuroscience Unit, University College, London, UK","Microsoft Research Limited, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Gatsby Computational Neuroscience Unit, University College, London, UK","institution_ids":["https://openalex.org/I4210115172","https://openalex.org/I45129253"]},{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108373424","display_name":"Neboj\u0161a Joji\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nebojsa Jojic","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110453625","display_name":"Hagai Attias","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hagai Attias","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111941455"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210115172","https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":0.6595,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.59965783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"II","last_page":"1997"},"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/T11309","display_name":"Music and Audio Processing","score":0.9952999949455261,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9950000047683716,"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":0.8249986171722412},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.5875669121742249},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5341020822525024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.52733314037323},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5152547955513},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5129711031913757},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5005245208740234},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5003674030303955},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.47102126479148865},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.4545726478099823},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.42380475997924805},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4177325665950775},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4108031392097473},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.331506609916687}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8249986171722412},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5875669121742249},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5341020822525024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.52733314037323},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5152547955513},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5129711031913757},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5005245208740234},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5003674030303955},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.47102126479148865},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.4545726478099823},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.42380475997924805},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4177325665950775},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4108031392097473},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.331506609916687},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2002.5745023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745023","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.16.8920","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.16.8920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gatsby.ucl.ac.uk/~beal/papers/icassp02.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W214562933","https://openalex.org/W1989461133","https://openalex.org/W2060843042","https://openalex.org/W2096198554","https://openalex.org/W2110412069","https://openalex.org/W2128764958","https://openalex.org/W2135265773","https://openalex.org/W2142511364","https://openalex.org/W2157190406","https://openalex.org/W6674716161"],"related_works":["https://openalex.org/W2407375987","https://openalex.org/W2505726097","https://openalex.org/W2950975704","https://openalex.org/W2010643158","https://openalex.org/W3049691116","https://openalex.org/W2106867672","https://openalex.org/W4310268968","https://openalex.org/W3081214562","https://openalex.org/W2053745677","https://openalex.org/W2189378472"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,12,17],"self-calibrating":[3],"algorithm":[4,15],"for":[5],"audio-visual":[6],"tracking":[7],"using":[8,98],"two":[9],"microphones":[10],"and":[11,27,48,56,78],"camera.":[13],"The":[14,65],"uses":[16],"parametrized":[18],"statistical":[19,51],"model":[20,33,66],"which":[21],"combines":[22],"simple":[23],"models":[24],"of":[25,53,85,94],"video":[26,57],"audio.":[28],"Using":[29],"unobserved":[30],"variables,":[31],"the":[32,35,39,50,54,71,95,99],"describes":[34],"process":[36],"that":[37],"generates":[38],"observed":[40],"data.":[41],"Hence,":[42],"it":[43],"is":[44,81,89,103],"able":[45],"to":[46],"capture":[47],"exploit":[49],"structure":[52],"audio":[55],"data,":[58],"as":[59,61,83],"well":[60],"their":[62],"mutual":[63],"dependencies,":[64],"parameters":[67],"are":[68,76],"estimated":[69],"by":[70,91],"EM":[72],"algorithm;":[73],"object":[74,96],"templates":[75],"learned":[77],"automatic":[79],"calibration":[80],"performed":[82],"part":[84],"this":[86],"procedure.":[87],"Tracking":[88],"done":[90],"Bayesian":[92],"inference":[93],"location":[97],"model.":[100],"Successful":[101],"performance":[102],"demonstrated":[104],"on":[105],"real":[106],"multimedia":[107],"clips.":[108]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}