{"id":"https://openalex.org/W2067627838","doi":"https://doi.org/10.1142/s1793351x12400077","title":"SPEECH SHOT EXTRACTION FROM BROADCAST NEWS VIDEOS","display_name":"SPEECH SHOT EXTRACTION FROM BROADCAST NEWS VIDEOS","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2067627838","doi":"https://doi.org/10.1142/s1793351x12400077","mag":"2067627838"},"language":"en","primary_location":{"id":"doi:10.1142/s1793351x12400077","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793351x12400077","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-351X","issn":["1793-351X","1793-7108"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","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/A5101144463","display_name":"Kumagai Shogo","orcid":null},"institutions":[{"id":"https://openalex.org/I24193003","display_name":"Ricoh (Japan)","ror":"https://ror.org/02h4myp42","country_code":"JP","type":"company","lineage":["https://openalex.org/I24193003"]},{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"SHOGO KUMAGAI","raw_affiliation_strings":["Currently at Ricoh Company, Ltd., Japan","Graduate School of Information Science, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi, 464-8601, Japan"],"affiliations":[{"raw_affiliation_string":"Currently at Ricoh Company, Ltd., Japan","institution_ids":["https://openalex.org/I24193003"]},{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi, 464-8601, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058196829","display_name":"Keisuke Doman","orcid":"https://orcid.org/0000-0001-6040-4988"},"institutions":[{"id":"https://openalex.org/I205924995","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466","country_code":"JP","type":"nonprofit","lineage":["https://openalex.org/I1319490839","https://openalex.org/I205924995"]},{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"KEISUKE DOMAN","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi, 464-8601, Japan","Japan Society for the Promotion of Science (JSPS), Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi, 464-8601, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Japan Society for the Promotion of Science (JSPS), Japan","institution_ids":["https://openalex.org/I205924995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112307441","display_name":"Tomokazu Takahashi","orcid":null},"institutions":[{"id":"https://openalex.org/I24286346","display_name":"Gifu Shotoku Gakuen University","ror":"https://ror.org/05tvatp40","country_code":"JP","type":"education","lineage":["https://openalex.org/I24286346"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"TOMOKAZU TAKAHASHI","raw_affiliation_strings":["Faculty of Economics and Information, Gifu Shotoku Gakuen University, 1-38 Nakauzura, Gifu, 500-8288, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Economics and Information, Gifu Shotoku Gakuen University, 1-38 Nakauzura, Gifu, 500-8288, Japan","institution_ids":["https://openalex.org/I24286346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054493960","display_name":"Daisuke Deguchi","orcid":"https://orcid.org/0000-0003-0603-8790"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"DAISUKE DEGUCHI","raw_affiliation_strings":["Information and Communications Headquarters, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi, 464-8601, Japan","Information and Communications Headquarters, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8601, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Information and Communications Headquarters, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi, 464-8601, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Information and Communications Headquarters, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8601, Japan#TAB#","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034941095","display_name":"Ichiro Ide","orcid":"https://orcid.org/0000-0003-3942-9296"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"ICHIRO IDE","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi, 464-8601, Japan","Graduate School of Information Science, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8601, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi, 464-8601, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8601, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085309296","display_name":"Hiroshi Murase","orcid":"https://orcid.org/0000-0002-8103-9294"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"HIROSHI MURASE","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi, 464-8601, Japan","Graduate School of Information Science, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8601, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi, 464-8601, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8601, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101144463"],"corresponding_institution_ids":["https://openalex.org/I24193003","https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":0.4897,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67093083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"06","issue":"02","first_page":"179","last_page":"204"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/shot","display_name":"Shot (pellet)","score":0.8917375802993774},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8646161556243896},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6572879552841187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5885263681411743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5056698322296143},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32337865233421326}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.8917375802993774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8646161556243896},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6572879552841187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5885263681411743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5056698322296143},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32337865233421326},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s1793351x12400077","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793351x12400077","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-351X","issn":["1793-351X","1793-7108"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6499999761581421}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327550","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W196476531","https://openalex.org/W1526146785","https://openalex.org/W1530227559","https://openalex.org/W1586636358","https://openalex.org/W1605811577","https://openalex.org/W1664825721","https://openalex.org/W1969228515","https://openalex.org/W2029888104","https://openalex.org/W2061489198","https://openalex.org/W2082942761","https://openalex.org/W2084514013","https://openalex.org/W2104686155","https://openalex.org/W2107985919","https://openalex.org/W2111459438","https://openalex.org/W2113814270","https://openalex.org/W2114327179","https://openalex.org/W2118847468","https://openalex.org/W2136155248","https://openalex.org/W2152826865","https://openalex.org/W2156909104","https://openalex.org/W2157363431","https://openalex.org/W2159591770","https://openalex.org/W2164598857","https://openalex.org/W2168311553","https://openalex.org/W4230674625","https://openalex.org/W4232401394","https://openalex.org/W4285719527","https://openalex.org/W4390545247"],"related_works":["https://openalex.org/W4214877189","https://openalex.org/W2074502265","https://openalex.org/W2381179799","https://openalex.org/W4287637665","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2728912566","https://openalex.org/W2380471679","https://openalex.org/W3192589309"],"abstract_inverted_index":{"We":[0],"propose":[1,108],"a":[2,7,11,20,30,67,109,114,118,136,139,185,189],"method":[3,110,130,156,181,205],"for":[4],"discriminating":[5],"between":[6,113,135,145,184],"speech":[8,17,51,115,171,186,199],"shot":[9,13,116,120,187],"and":[10,38,64,117,138,148,162,188],"narrated":[12,101,119,190],"to":[14,49,74,111],"extract":[15,50,75],"genuine":[16],"shots":[18,25,52,87,200],"from":[19,53],"broadcast":[21],"news":[22,27,54,83],"video.":[23],"Speech":[24],"in":[26,97,121],"videos":[28,84],"contain":[29,85],"wealth":[31],"of":[32,35,66,127,153,170,176,198,213],"multimedia":[33],"information":[34],"the":[36,62,89,93,98,128,133,143,154,160,168,174,179,193,195,203,211,214],"speaker,":[37],"could":[39],"thus":[40],"be":[41],"considered":[42],"valuable":[43],"as":[44],"archived":[45],"material.":[46],"In":[47,192],"order":[48],"videos,":[55],"there":[56],"is":[57,72,91],"an":[58,80],"approach":[59],"that":[60,95,165],"uses":[61],"position":[63],"size":[65],"face":[68],"region.":[69],"However,":[70],"it":[71],"difficult":[73],"them":[76],"with":[77],"only":[78],"such":[79],"approach,":[81],"since":[82],"non-speech":[86],"where":[88],"speaker":[90,140],"not":[92],"subject":[94,137],"appears":[96],"screen,":[99],"namely,":[100],"shots.":[102,172],"To":[103],"solve":[104],"this":[105],"problem,":[106],"we":[107,209],"discriminate":[112],"two":[122],"stages.":[123],"The":[124,150],"first":[125],"stage":[126,152],"proposed":[129,155,180,204,215],"directly":[131],"evaluates":[132,157],"inconsistency":[134],"based":[141,158],"on":[142,159,167],"co-occurrence":[144],"lip":[146],"motion":[147],"voice.":[149],"second":[151],"intra-":[161],"inter-shot":[163],"features":[164],"focus":[166],"tendency":[169],"With":[173],"combination":[175],"both":[177],"stages,":[178],"accurately":[182],"discriminates":[183],"shot.":[191],"experiments,":[194],"overall":[196],"accuracy":[197],"extraction":[201],"by":[202],"was":[206],"0.871.":[207],"Therefore,":[208],"confirmed":[210],"effectiveness":[212],"method.":[216]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
