{"id":"https://openalex.org/W2100366204","doi":"https://doi.org/10.1109/cvprw.2009.5204303","title":"Audio-visual speech synchronization detection using a bimodal linear prediction model","display_name":"Audio-visual speech synchronization detection using a bimodal linear prediction model","publication_year":2009,"publication_date":"2009-06-01","ids":{"openalex":"https://openalex.org/W2100366204","doi":"https://doi.org/10.1109/cvprw.2009.5204303","mag":"2100366204"},"language":"en","primary_location":{"id":"doi:10.1109/cvprw.2009.5204303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw.2009.5204303","pdf_url":null,"source":{"id":"https://openalex.org/S4363608118","display_name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","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":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","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/A5047826067","display_name":"Kshitiz Kumar","orcid":"https://orcid.org/0000-0003-2728-2493"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kshitiz Kumar","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039085741","display_name":"Ji\u0159\u00ed Navr\u00e1til","orcid":"https://orcid.org/0000-0001-6348-0812"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiri Navratil","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","T. J. Watson Res. Center, IBM, Yorktown Heights, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"T. J. Watson Res. Center, IBM, Yorktown Heights, NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010196081","display_name":"Etienne Marcheret","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Etienne Marcheret","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","T. J. Watson Res. Center, IBM, Yorktown Heights, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"T. J. Watson Res. Center, IBM, Yorktown Heights, NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047716643","display_name":"Vit Libal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vit Libal","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","T. J. Watson Res. Center, IBM, Yorktown Heights, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"T. J. Watson Res. Center, IBM, Yorktown Heights, NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111944718","display_name":"Ganesh N. Ramaswamy","orcid":"https://orcid.org/0009-0002-8015-0844"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ganesh Ramaswamy","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","T. J. Watson Res. Center, IBM, Yorktown Heights, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"T. J. Watson Res. Center, IBM, Yorktown Heights, NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[{"id":"https://openalex.org/I4387152169","display_name":"Institute of Informatics & Telecommunications","ror":"https://ror.org/0396t6k89","country_code":null,"type":"facility","lineage":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]},{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":["NCSR Demokritos, Institute of Informatics and Telecommunications, Athens, Greece","Inst. of Inf. & Telecommun., NCSR, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"NCSR Demokritos, Institute of Informatics and Telecommunications, Athens, Greece","institution_ids":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]},{"raw_affiliation_string":"Inst. of Inf. & Telecommun., NCSR, Athens, Greece","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5047826067"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":4.0898,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.95023697,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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":0.8139208555221558},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.7027627825737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6494874358177185},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.6012938618659973},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.5834224224090576},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.5294831395149231},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5178083181381226},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5081353187561035},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4595555067062378},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4457703232765198},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3628942370414734}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8139208555221558},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.7027627825737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6494874358177185},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.6012938618659973},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.5834224224090576},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.5294831395149231},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5178083181381226},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5081353187561035},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4595555067062378},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4457703232765198},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3628942370414734},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvprw.2009.5204303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw.2009.5204303","pdf_url":null,"source":{"id":"https://openalex.org/S4363608118","display_name":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","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":"2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W1988910659","https://openalex.org/W2033178790","https://openalex.org/W2100235303","https://openalex.org/W2100561338","https://openalex.org/W2118847468","https://openalex.org/W2159997200","https://openalex.org/W2164899449","https://openalex.org/W2168744723","https://openalex.org/W6675048546","https://openalex.org/W6678139733"],"related_works":["https://openalex.org/W2188559950","https://openalex.org/W2989910292","https://openalex.org/W2998478967","https://openalex.org/W3128793638","https://openalex.org/W2123299109","https://openalex.org/W2021230337","https://openalex.org/W4401097268","https://openalex.org/W2607818178","https://openalex.org/W3153057489","https://openalex.org/W2281508611"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,55],"study":[4],"the":[5,53,70,92,102,111,129,134],"problem":[6,23],"of":[7,72,87],"detecting":[8],"audio-visual":[9],"(AV)":[10],"synchronization":[11,73],"in":[12,18,27,39,47],"video":[13],"segments":[14],"containing":[15],"a":[16,57,121],"speaker":[17,49],"frontal":[19],"head":[20],"pose.":[21],"The":[22],"holds":[24],"important":[25,37],"applications":[26],"biometrics,":[28],"for":[29,43,60],"example":[30],"spoofing":[31],"detection,":[32],"and":[33,63,98],"it":[34],"constitutes":[35],"an":[36,65,80],"step":[38],"AV":[40,45,61,82,117],"segmentation":[41],"necessary":[42],"deriving":[44],"fingerprints":[46],"multimodal":[48],"recognition.":[50],"To":[51],"attack":[52],"problem,":[54],"propose":[56],"time-evolution":[58],"model":[59],"features":[62,89,99,132],"derive":[64],"analytical":[66],"approach":[67,113],"to":[68],"capture":[69],"notion":[71],"between":[74],"them.":[75],"We":[76],"report":[77],"results":[78,108],"on":[79,101],"appropriate":[81],"database,":[83],"using":[84],"two":[85],"types":[86],"visual":[88,131],"extracted":[90],"from":[91],"speaker's":[93],"facial":[94],"area:":[95],"geometric":[96,130],"ones":[97],"based":[100],"discrete":[103],"cosine":[104],"image":[105,135],"transform.":[106],"Our":[107],"demonstrate":[109],"that":[110,124],"proposed":[112],"provides":[114],"substantially":[115],"better":[116],"synchrony":[118],"detection":[119],"over":[120],"baseline":[122],"method":[123],"employs":[125],"mutual":[126],"information,":[127],"with":[128],"outperforming":[133],"transform":[136],"ones.":[137]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
