{"id":"https://openalex.org/W1975098367","doi":"https://doi.org/10.1002/(sici)1520-684x(19981115)29:12<1::aid-scj1>3.0.co;2-3","title":"A sound-based approach to video indexing and its application","display_name":"A sound-based approach to video indexing and its application","publication_year":1998,"publication_date":"1998-11-15","ids":{"openalex":"https://openalex.org/W1975098367","doi":"https://doi.org/10.1002/(sici)1520-684x(19981115)29:12<1::aid-scj1>3.0.co;2-3","mag":"1975098367"},"language":"en","primary_location":{"id":"doi:10.1002/(sici)1520-684x(19981115)29:12<1::aid-scj1>3.0.co;2-3","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1520-684x(19981115)29:12<1::aid-scj1>3.0.co;2-3","pdf_url":null,"source":{"id":"https://openalex.org/S58208175","display_name":"Systems and Computers in Japan","issn_l":"0882-1666","issn":["0882-1666","1520-684X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Systems and Computers in Japan","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/A5013518316","display_name":"Kenichi Minami","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenichi Minami","raw_affiliation_strings":["NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239-0847","NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239\u20100847"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239-0847","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239\u20100847","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052485933","display_name":"Akihito Akutsu","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihito Akutsu","raw_affiliation_strings":["NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239-0847","NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239\u20100847"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239-0847","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239\u20100847","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087581054","display_name":"Hiroshi Hamada","orcid":"https://orcid.org/0000-0002-8637-1843"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Hamada","raw_affiliation_strings":["NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239-0847","NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239\u20100847"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239-0847","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239\u20100847","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113542879","display_name":"Yoshinobu Tonomura","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshinobu Tonomura","raw_affiliation_strings":["NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239-0847","NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239\u20100847"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239-0847","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Human Interface Laboratories, Nippon Telegraph and Telephone Corporation, Kanagawa, Japan 239\u20100847","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.12810248,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":"12","first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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":0.9998999834060669,"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":0.9911999702453613,"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":0.7736092805862427},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6148024201393127},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5745779871940613},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5608249306678772},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4927072823047638},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.45789605379104614},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.45358091592788696},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.43916943669319153},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.43542930483818054},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4293527603149414},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.40178728103637695},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.33374854922294617},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3277384638786316},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2805076241493225},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.17848539352416992},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.10296106338500977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7736092805862427},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6148024201393127},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5745779871940613},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5608249306678772},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4927072823047638},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.45789605379104614},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.45358091592788696},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.43916943669319153},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.43542930483818054},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4293527603149414},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.40178728103637695},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.33374854922294617},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3277384638786316},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2805076241493225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.17848539352416992},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.10296106338500977},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","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},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/(sici)1520-684x(19981115)29:12<1::aid-scj1>3.0.co;2-3","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1520-684x(19981115)29:12<1::aid-scj1>3.0.co;2-3","pdf_url":null,"source":{"id":"https://openalex.org/S58208175","display_name":"Systems and Computers in Japan","issn_l":"0882-1666","issn":["0882-1666","1520-684X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Systems and Computers in Japan","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W120629929","https://openalex.org/W1551816323","https://openalex.org/W1558920084","https://openalex.org/W1776985898","https://openalex.org/W1964000405","https://openalex.org/W1994424184","https://openalex.org/W2004367373","https://openalex.org/W2006830243","https://openalex.org/W2048764735","https://openalex.org/W2074188409","https://openalex.org/W2078306367","https://openalex.org/W2099886908","https://openalex.org/W2112306108","https://openalex.org/W2117123688","https://openalex.org/W2119339729","https://openalex.org/W2135539886","https://openalex.org/W2137542411","https://openalex.org/W6638180245","https://openalex.org/W6677514742"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2088690926","https://openalex.org/W1590604789","https://openalex.org/W1479881079","https://openalex.org/W1975359510","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W3004352674"],"abstract_inverted_index":{"We":[0,69],"have":[1],"been":[2],"carrying":[3],"out":[4],"research":[5],"on":[6],"intelligent":[7],"video":[8,201],"interfaces":[9],"to":[10,21,43,125,172],"improve":[11],"the":[12,26,29,32,37,44,48,51,54,59,64,67,77,81,117,121,129,143,146,156,173],"manipulation":[13],"of":[14,25,31,36,53,66,80,120,136,145,158,176,184],"videos":[15,38],"for":[16,102,132,196],"searching,":[17],"editing,":[18],"processing":[19],"and":[20,50,93,106,148,192,199,203],"support":[22],"rapid":[23],"review":[24],"contents":[27,202],"using":[28,151,165],"characteristics":[30,79],"videos.":[33],"The":[34],"soundtracks":[35],"contain":[39],"much":[40],"information":[41],"related":[42],"events":[45,74],"occurring":[46],"in":[47,128],"scenes":[49],"situations":[52],"scenes.":[55],"They":[56],"also":[57],"reflect":[58],"director's":[60],"intentions":[61],"expressed":[62],"through":[63],"emotions":[65],"cast.":[68],"can":[70,84],"often":[71],"estimate":[72],"these":[73],"directly":[75],"from":[76],"physical":[78],"sound.":[82,178],"Sound":[83],"be":[85,126],"classified":[86],"into":[87],"three":[88],"major":[89],"categories:":[90],"music,":[91],"speech,":[92,107],"sound":[94,122],"effects.":[95],"In":[96],"this":[97],"paper,":[98],"we":[99,180],"propose":[100],"algorithms":[101],"independently":[103],"detecting":[104],"music":[105,114,191],"even":[108],"if":[109],"they":[110],"occur":[111],"together.":[112],"When":[113],"is":[115,139,162,170],"present,":[116],"spectrum":[118],"peaks":[119,147],"data":[123],"appear":[124],"stable":[127],"frequency":[130],"direction":[131],"a":[133,166],"certain":[134],"period":[135],"time.":[137],"Music":[138],"detected":[140,163,190],"by":[141,164],"obtaining":[142],"positions":[144],"their":[149],"duration":[150],"an":[152,182,185],"edge":[153],"operator.":[154],"After":[155],"removal":[157],"musical":[159],"components,":[160],"speech":[161,193],"comb":[167],"filter":[168],"that":[169,188],"sensitive":[171],"harmonic":[174],"structure":[175],"vocal":[177],"Further,":[179],"present":[181],"example":[183],"application":[186],"interface":[187],"uses":[189],"as":[194],"indexes":[195],"browsing,":[197],"accessing,":[198],"surveying":[200],"discuss":[204],"its":[205],"effectiveness.":[206],"\u00a9":[207],"1998":[208,216],"Scripta":[209],"Technica,":[210],"Syst":[211],"Comp":[212],"Jpn,":[213],"29(12):":[214],"1\u201310,":[215]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
