{"id":"https://openalex.org/W2106694147","doi":"https://doi.org/10.1109/tcsvt.2008.2005613","title":"Audio-Assisted Movie Dialogue Detection","display_name":"Audio-Assisted Movie Dialogue Detection","publication_year":2008,"publication_date":"2008-09-26","ids":{"openalex":"https://openalex.org/W2106694147","doi":"https://doi.org/10.1109/tcsvt.2008.2005613","mag":"2106694147"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2008.2005613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2008.2005613","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":true,"oa_status":"green","oa_url":"http://doi.org/10.1109/TCSVT.2008.2005613","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031329337","display_name":"Margarita Kotti","orcid":"https://orcid.org/0000-0003-4212-7037"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"M. Kotti","raw_affiliation_strings":["Dept. of Inf., Aristotle Univ. of Thessaloniki, Thessaloniki"],"affiliations":[{"raw_affiliation_string":"Dept. of Inf., Aristotle Univ. of Thessaloniki, Thessaloniki","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064028058","display_name":"Dimitrios Ververidis","orcid":"https://orcid.org/0000-0001-7799-6502"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"D. Ververidis","raw_affiliation_strings":["Dept. of Inf., Aristotle Univ. of Thessaloniki, Thessaloniki"],"affiliations":[{"raw_affiliation_string":"Dept. of Inf., Aristotle Univ. of Thessaloniki, Thessaloniki","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043020206","display_name":"Georgios Evangelopoulos","orcid":"https://orcid.org/0000-0003-2240-1801"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"G. Evangelopoulos","raw_affiliation_strings":["School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050734738","display_name":"Yannis Panagakis","orcid":"https://orcid.org/0000-0003-0153-5210"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"I. Panagakis","raw_affiliation_strings":["Department of Informatics, Aristotle University of Thessaloniki , Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Aristotle University of Thessaloniki , Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065184406","display_name":"Constantine Kotropoulos","orcid":"https://orcid.org/0000-0001-9939-7930"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"C. Kotropoulos","raw_affiliation_strings":["Department of Informatics, Aristotle University of Thessaloniki , Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Aristotle University of Thessaloniki , Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079243420","display_name":"Petros Maragos","orcid":"https://orcid.org/0000-0003-0534-2707"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"P. Maragos","raw_affiliation_strings":["School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061130224","display_name":"Ioannis Pitas","orcid":"https://orcid.org/0009-0006-7555-8641"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"I. Pitas","raw_affiliation_strings":["Department of Informatics, Aristotle University of Thessaloniki , Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Aristotle University of Thessaloniki , Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5031329337"],"corresponding_institution_ids":["https://openalex.org/I21370196"],"apc_list":null,"apc_paid":null,"fwci":0.3798,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.62742671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"18","issue":"11","first_page":"1618","last_page":"1627"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9979000091552734,"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":0.6902477741241455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4629092812538147},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4201369285583496},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.33450600504875183},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3259914219379425}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6902477741241455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4629092812538147},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4201369285583496},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33450600504875183},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3259914219379425}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tcsvt.2008.2005613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2008.2005613","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:eprints.mdx.ac.uk:23758","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400025","display_name":"Middlesex University Research Repository (Middlesex University Of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60488453","host_organization_name":"Middlesex University","host_organization_lineage":["https://openalex.org/I60488453"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.331.1828","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.331.1828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cvsp.cs.ntua.gr/publications/jpubl+bchap/Kotti_Audio-Assisted Movie Dialogue Detection_ieeeTCSVT2008.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/18655","is_oa":true,"landing_page_url":"http://doi.org/10.1109/TCSVT.2008.2005613","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/11709","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/11709","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"1627","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/18655","is_oa":true,"landing_page_url":"http://doi.org/10.1109/TCSVT.2008.2005613","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W59325952","https://openalex.org/W60398317","https://openalex.org/W195134767","https://openalex.org/W1238127590","https://openalex.org/W1489724581","https://openalex.org/W1505909218","https://openalex.org/W1512098439","https://openalex.org/W1514558801","https://openalex.org/W1538113785","https://openalex.org/W1550519762","https://openalex.org/W1570448133","https://openalex.org/W1579631645","https://openalex.org/W1748915547","https://openalex.org/W1904447473","https://openalex.org/W1979711143","https://openalex.org/W1993625798","https://openalex.org/W2005671413","https://openalex.org/W2029687556","https://openalex.org/W2062497323","https://openalex.org/W2091181450","https://openalex.org/W2100683356","https://openalex.org/W2114537326","https://openalex.org/W2115717467","https://openalex.org/W2141929195","https://openalex.org/W2143956139","https://openalex.org/W2145073242","https://openalex.org/W2149523328","https://openalex.org/W2149759367","https://openalex.org/W2156567019","https://openalex.org/W2159997200","https://openalex.org/W2164098787","https://openalex.org/W2166980079","https://openalex.org/W2171315576","https://openalex.org/W2171700247","https://openalex.org/W3083074837","https://openalex.org/W3085162807","https://openalex.org/W3139866291","https://openalex.org/W4249572517","https://openalex.org/W6637983305","https://openalex.org/W6681651645"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2058170566","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2079911747"],"abstract_inverted_index":{"Abstract\u2014An":[0],"audio-assisted":[1],"system":[2,17],"is":[3,11,18,85,158],"investigated":[4],"that":[5],"detects":[6],"if":[7,29],"a":[8,12,34,53],"movie":[9],"scene":[10],"dialogue":[13,104,138,145,168],"or":[14],"not.":[15],"The":[16,88],"based":[19],"on":[20],"actor":[21,31,124],"indicator":[22,56,96,114,170],"functions.":[23],"That":[24],"is,":[25],"functions":[26,57,97,115],"which":[27,142],"define":[28],"an":[30],"speaks":[32],"at":[33],"certain":[35],"time":[36],"instant.":[37],"In":[38],"particular,":[39],"the":[40,43,46,48,135],"cross-correlation":[41],"and":[42,73,105,123,147,156],"magnitude":[44],"of":[45,52,55,141],"corresponding":[47],"cross-power":[49],"spectral":[50,166],"density":[51],"pair":[54],"are":[58,91,116,131],"input":[59],"to":[60,126,144,149],"various":[61],"classifiers,":[62],"such":[63],"as":[64],"voted":[65],"perceptrons,":[66],"radial":[67],"basis":[68],"function":[69],"networks,":[70],"random":[71],"trees,":[72],"support":[74],"vector":[75],"machines":[76],"for":[77,102],"dialogue/non-dialogue":[78],"detection.":[79],"To":[80],"boost":[81],"classifier":[82],"efficiency":[83],"AdaBoost":[84],"also":[86],"exploited.":[87],"aforementioned":[89,136],"classifiers":[90],"trained":[92],"using":[93],"ground":[94],"truth":[95],"determined":[98],"by":[99,118],"human":[100],"annotators":[101],"41":[103,137],"another":[106],"20":[107],"non-dialogue":[108,150],"audio":[109,120,127],"instances.":[110],"For":[111],"testing,":[112],"actual":[113],"derived":[117],"applying":[119],"activity":[121,162],"detection":[122],"clustering":[125],"recordings.":[128],"23":[129],"instances":[130],"randomly":[132],"chosen":[133],"among":[134],"instances,":[139],"17":[140],"correspond":[143],"scenes":[146],"6":[148],"ones.":[151],"Accuracy":[152],"ranging":[153],"between":[154],"0.739":[155],"0.826":[157],"reported.":[159],"Index":[160],"Terms\u2014Audio":[161],"detection,":[163,169],"cross-correlation,":[164],"crosspower":[165],"density,":[167],"functions,":[171],"speaker":[172],"clustering.":[173],"I.":[174]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}