{"id":"https://openalex.org/W2043930378","doi":"https://doi.org/10.1109/icassp.2011.5946937","title":"Audio-visual synchronization recovery in multimedia content","display_name":"Audio-visual synchronization recovery in multimedia content","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2043930378","doi":"https://doi.org/10.1109/icassp.2011.5946937","mag":"2043930378"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946937","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/162356","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100668167","display_name":"Jong\u2010Seok Lee","orcid":"https://orcid.org/0000-0002-8038-1119"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Jong-Seok Lee","raw_affiliation_strings":["Multimedia Signal Processing Group (MMSPG), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","Multimedia Signal Processing Group (MMSPG), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), CH-1015, Switzerland"],"affiliations":[{"raw_affiliation_string":"Multimedia Signal Processing Group (MMSPG), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Multimedia Signal Processing Group (MMSPG), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), CH-1015, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082188773","display_name":"Touradj Ebrahimi","orcid":"https://orcid.org/0000-0002-9900-3687"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Touradj Ebrahimi","raw_affiliation_strings":["Multimedia Signal Processing Group (MMSPG), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","Multimedia Signal Processing Group (MMSPG), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), CH-1015, Switzerland"],"affiliations":[{"raw_affiliation_string":"Multimedia Signal Processing Group (MMSPG), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Multimedia Signal Processing Group (MMSPG), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), CH-1015, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100668167"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":0.9354,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73869772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2280","last_page":"2283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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":0.9980999827384949,"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":0.982200026512146,"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/T12032","display_name":"Multisensory perception and integration","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.8243074417114258},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7923386096954346},{"id":"https://openalex.org/keywords/canonical-correlation","display_name":"Canonical correlation","score":0.7828157544136047},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7636654376983643},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.6512569785118103},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5608974695205688},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5378913283348083},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5288639664649963},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5228505730628967},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47706592082977295},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.41534435749053955},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33630234003067017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32044801115989685},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.31493502855300903},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.22643297910690308},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12009930610656738},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09309816360473633}],"concepts":[{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.8243074417114258},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7923386096954346},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.7828157544136047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7636654376983643},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.6512569785118103},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5608974695205688},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5378913283348083},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5288639664649963},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5228505730628967},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47706592082977295},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.41534435749053955},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33630234003067017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32044801115989685},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.31493502855300903},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.22643297910690308},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12009930610656738},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09309816360473633},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp.2011.5946937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946937","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1022.3808","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1022.3808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Touradj_Ebrahimi/publication/224246164_Audio-visual_synchronization_recovery_in_multimedia_content/links/00463515b3d9875ecc000000.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1025.8615","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1025.8615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mirlab.org/conference_papers/International_Conference/ICASSP%202011/pdfs/0002280.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.362.1232","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.362.1232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/162356/files/lee_icassp11.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:162356","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/162356","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:162356","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/63060","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:162356","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/162356","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1578856370","https://openalex.org/W2071932093","https://openalex.org/W2090856384","https://openalex.org/W2098923380","https://openalex.org/W2100235303","https://openalex.org/W2100461058","https://openalex.org/W2119871260","https://openalex.org/W6675190910"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3],"method":[4,80],"recovering":[5,88],"audio-visual":[6,27,58,90],"synchronization":[7,91],"of":[8,45],"multimedia":[9],"content.":[10,32],"It":[11],"exploits":[12],"the":[13,16,19,26,31,35,40,43,46,53,56,79,82,89],"correlation":[14,63,84],"between":[15],"acoustic":[17],"and":[18,68,71,95],"visual":[20,41],"signals":[21],"in":[22,30,87],"order":[23],"to":[24,39],"estimate":[25],"drift":[28,47],"existing":[29],"By":[33],"shifting":[34],"audio":[36],"signal":[37],"relative":[38],"signal,":[42],"estimation":[44],"is":[48,85],"obtained":[49],"by":[50],"searching":[51],"for":[52,92],"shift":[54],"producing":[55],"maximal":[57],"correlation.":[59],"We":[60],"consider":[61],"two":[62],"measures,":[64],"namely,":[65],"mutual":[66],"information":[67],"canonical":[69,83],"correlation,":[70],"compare":[72],"their":[73],"performance.":[74],"Experimental":[75],"results":[76],"demonstrate":[77],"that":[78],"using":[81],"effective":[86],"both":[93],"speech":[94],"non-speech":[96],"sequences.":[97]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
