{"id":"https://openalex.org/W2114032116","doi":"https://doi.org/10.1109/tcsvt.2008.2005602","title":"Exploring Co-Occurence Between Speech and Body Movement for Audio-Guided Video Localization","display_name":"Exploring Co-Occurence Between Speech and Body Movement for Audio-Guided Video Localization","publication_year":2008,"publication_date":"2008-09-29","ids":{"openalex":"https://openalex.org/W2114032116","doi":"https://doi.org/10.1109/tcsvt.2008.2005602","mag":"2114032116"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2008.2005602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2008.2005602","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5088240246","display_name":"Himanshu Vajaria","orcid":null},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Vajaria","raw_affiliation_strings":["University of South Florida, Tampa, FL, USA","South Florida, Univ., Tampa, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Florida, Tampa, FL, USA","institution_ids":["https://openalex.org/I2613432"]},{"raw_affiliation_string":"South Florida, Univ., Tampa, FL","institution_ids":["https://openalex.org/I2613432"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020674314","display_name":"Sudeep Sarkar","orcid":"https://orcid.org/0000-0001-7332-4207"},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Sarkar","raw_affiliation_strings":["University of South Florida, Tampa, FL, USA","South Florida, Univ., Tampa, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Florida, Tampa, FL, USA","institution_ids":["https://openalex.org/I2613432"]},{"raw_affiliation_string":"South Florida, Univ., Tampa, FL","institution_ids":["https://openalex.org/I2613432"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063184621","display_name":"Rangachar Kasturi","orcid":"https://orcid.org/0000-0003-3956-1967"},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Kasturi","raw_affiliation_strings":["University of South Florida, Tampa, FL, USA","South Florida, Univ., Tampa, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Florida, Tampa, FL, USA","institution_ids":["https://openalex.org/I2613432"]},{"raw_affiliation_string":"South Florida, Univ., Tampa, FL","institution_ids":["https://openalex.org/I2613432"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2613432"],"apc_list":null,"apc_paid":null,"fwci":1.9615,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.86705508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"18","issue":"11","first_page":"1608","last_page":"1617"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7737321853637695},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6902908086776733},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6883669495582581},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.604428768157959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4935225248336792},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.481894314289093},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4698352515697479},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4660998582839966},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4631824493408203},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.40475350618362427},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36765599250793457},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3235664963722229}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7737321853637695},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6902908086776733},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6883669495582581},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.604428768157959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4935225248336792},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.481894314289093},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4698352515697479},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4660998582839966},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4631824493408203},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.40475350618362427},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36765599250793457},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3235664963722229},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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":2,"locations":[{"id":"doi:10.1109/tcsvt.2008.2005602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2008.2005602","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.420.7029","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.420.7029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-gth.die.upm.es/research/documentation/referencias/Vajaria_Exploring.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W140783384","https://openalex.org/W1499712254","https://openalex.org/W1509663858","https://openalex.org/W1524280659","https://openalex.org/W1539515721","https://openalex.org/W1567497459","https://openalex.org/W2029192628","https://openalex.org/W2035090801","https://openalex.org/W2041823554","https://openalex.org/W2046845112","https://openalex.org/W2099403067","https://openalex.org/W2100561338","https://openalex.org/W2105582566","https://openalex.org/W2110933444","https://openalex.org/W2113386290","https://openalex.org/W2117766076","https://openalex.org/W2118847468","https://openalex.org/W2132920253","https://openalex.org/W2135211394","https://openalex.org/W2148659689","https://openalex.org/W2154636774","https://openalex.org/W2159591770","https://openalex.org/W2164899449","https://openalex.org/W2171819471","https://openalex.org/W2398758317","https://openalex.org/W2416156489","https://openalex.org/W2915347754","https://openalex.org/W3160125816","https://openalex.org/W6630463007","https://openalex.org/W6631637966","https://openalex.org/W6632367477","https://openalex.org/W6633772420","https://openalex.org/W6675048546","https://openalex.org/W6679214204","https://openalex.org/W6684193366"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1197719229","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2381158726","https://openalex.org/W2552734076","https://openalex.org/W2162158162","https://openalex.org/W1992796048","https://openalex.org/W1999004162"],"abstract_inverted_index":{"This":[0,135],"paper":[1],"presents":[2],"a":[3,32,37,97,108,124,144,171,211,225,255],"bottom-up":[4],"approach":[5,80,252,277],"that":[6,143,248,265],"combines":[7],"audio":[8,86,95],"and":[9,22,36,87,155,175,193,206,228,264,282],"video":[10,18,88,118],"to":[11,56,128,254],"simultaneously":[12],"locate":[13],"individual":[14],"speakers":[15],"in":[16,28,43,116,236],"the":[17,48,54,79,94,117,130,140,150,160,176,186,191,201,208,222,229,234,237,249],"(2D":[19],"source":[20],"localization)":[21],"segment":[23],"their":[24],"speech":[25,105,141,223],"(speaker":[26],"diarization),":[27],"meetings":[29],"recorded":[30],"by":[31,123,170,181,199,269,271],"single":[33,38,109,226],"stationary":[34],"camera":[35],"microphone.":[39],"The":[40,275],"novelty":[41],"lies":[42],"using":[44],"motion":[45],"information":[46],"from":[47,106,159,164,224],"entire":[49],"body":[50,69],"rather":[51],"than":[52,149],"just":[53],"face":[55],"perform":[57],"these":[58],"tasks,":[59],"which":[60],"permits":[61],"processing":[62],"nonfrontal":[63],"views,":[64],"unlike":[65],"previous":[66],"work.":[67],"Since":[68],"movements":[70],"do":[71],"not":[72,279,284],"exhibit":[73],"instantaneous":[74],"signal-level":[75],"synchrony":[76],"with":[77,139],"speech,":[78],"targets":[81],"long":[82],"term":[83],"co-occurrences":[84],"between":[85],"subspaces.":[89],"First,":[90],"temporal":[91],"clustering":[92,113,189],"of":[93,100,120,132,173,204,244,258],"produces":[96],"large":[98],"number":[99],"intermediate":[101,161,166],"clusters,":[102],"each":[103,121,217],"containing":[104],"only":[107],"speaker.":[110],"Then,":[111],"spatial":[112],"is":[114,137,157,168,179,214],"performed":[115],"frames":[119],"cluster":[122,167,219],"novel":[125],"eigen-analysis":[126],"method":[127],"find":[129],"region":[131,136],"dominant":[133],"motion.":[134],"associated":[138],"assuming":[142],"speaker":[145,227,235,266],"exhibits":[146],"more":[147],"movement":[148],"listeners.":[151],"Thus,":[152],"partial":[153],"diarization":[154,192,267],"localization":[156,194,251,263],"obtained":[158],"clusters.":[162],"Speech":[163],"an":[165,182],"modeled":[169],"mixture":[172],"Gaussians":[174],"speaker's":[177],"location":[178],"represented":[180],"eigen-blob":[183,231],"model.":[184],"In":[185],"ensuing":[187],"iterative":[188],"stage,":[190],"results":[195],"are":[196],"progressively":[197],"refined":[198],"merging":[200],"closest":[202],"pair":[203],"clusters":[205],"updating":[207],"models":[209],"until":[210],"stop":[212],"criterion":[213],"met.":[215],"Ideally,":[216],"final":[218],"contains":[220],"all":[221],"corresponding":[230],"model":[232],"localizes":[233],"image.":[238],"Experiments":[239],"conducted":[240],"on":[241],"21":[242],"h":[243],"real":[245],"data":[246],"indicate":[247],"proposed":[250,276],"leads":[253],"relative":[256],"improvement":[257],"40%":[259],"over":[260],"mutual":[261],"information-based":[262],"improves":[268],"16%":[270],"incorporating":[272],"visual":[273],"information.":[274],"does":[278,283],"require":[280],"training":[281],"rely":[285],"onapriorihand/face/person":[286],"detection.":[287]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}