{"id":"https://openalex.org/W1495425814","doi":"https://doi.org/10.1109/icme.2015.7177422","title":"Visualizing video sounds with sound word animation","display_name":"Visualizing video sounds with sound word animation","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W1495425814","doi":"https://doi.org/10.1109/icme.2015.7177422","mag":"1495425814"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2015.7177422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2015.7177422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5088412694","display_name":"Fangzhou Wang","orcid":"https://orcid.org/0000-0002-9640-5285"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fangzhou Wang","raw_affiliation_strings":["The University of Tokyo","The University of Tokyo, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, JAPAN","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112254783","display_name":"Hidehisa Nagano","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":"Hidehisa Nagano","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation","NTT Communication Science Labs, NTT Corp., Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs, NTT Corp., Japan#TAB#","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061465935","display_name":"Kunio Kashino","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":"Kunio Kashino","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation","NTT Communication Science Labs, NTT Corp., Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs, NTT Corp., Japan#TAB#","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102743150","display_name":"Takeo Igarashi","orcid":"https://orcid.org/0000-0002-5495-6441"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeo Igarashi","raw_affiliation_strings":["The University of Tokyo","The University of Tokyo, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, JAPAN","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9947999715805054,"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":0.9944000244140625,"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":0.8006588220596313},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.7449595928192139},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6455162763595581},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6079234480857849},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4469248950481415},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4363483190536499},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3760991394519806},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34905827045440674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27499717473983765},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15632978081703186},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.1507354974746704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8006588220596313},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.7449595928192139},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6455162763595581},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6079234480857849},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4469248950481415},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4363483190536499},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3760991394519806},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34905827045440674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27499717473983765},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15632978081703186},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.1507354974746704},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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:10.1109/icme.2015.7177422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2015.7177422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1503007957","https://openalex.org/W1555152292","https://openalex.org/W1567619397","https://openalex.org/W1580529010","https://openalex.org/W1968589407","https://openalex.org/W2030371206","https://openalex.org/W2035140157","https://openalex.org/W2050968192","https://openalex.org/W2074188409","https://openalex.org/W2130640900","https://openalex.org/W2147853020","https://openalex.org/W2168356304","https://openalex.org/W4253161066","https://openalex.org/W4361983081","https://openalex.org/W6633908967"],"related_works":["https://openalex.org/W4310844315","https://openalex.org/W2532377291","https://openalex.org/W2000013817","https://openalex.org/W2068608913","https://openalex.org/W4296190881","https://openalex.org/W2909726438","https://openalex.org/W3124914020","https://openalex.org/W2366362996","https://openalex.org/W2517624617","https://openalex.org/W2378422373"],"abstract_inverted_index":{"Text":[0],"captions":[1,20],"are":[2,21,30],"important":[3],"means":[4],"to":[5,32,50,127],"provide":[6],"sound":[7,13,52,59,80,103,115,122],"information":[8,77],"in":[9,62],"videos":[10],"when":[11],"the":[12,58,63,79,112,118,121,135,139],"is":[14],"not":[15,106],"accessible.":[16],"However,":[17],"conventional":[18],"text":[19],"far":[22],"less":[23],"expressive":[24],"for":[25,44,65],"non-verbal":[26,47,73],"sounds":[27,49,74],"since":[28],"they":[29],"designed":[31],"visualize":[33,111],"speech":[34],"sound.":[35],"To":[36],"address":[37],"this":[38],"problem,":[39],"we":[40],"propose":[41],"a":[42,86],"method":[43],"automatically":[45],"transforming":[46],"video":[48,64,129],"animated":[51,102],"words,":[53],"and":[54,82,109,133],"positioning":[55],"them":[56],"near":[57],"source":[60],"objects":[61],"visualization.":[66],"This":[67],"provides":[68],"natural":[69],"visual":[70,136],"representation":[71],"of":[72,114,120,138],"with":[75,89],"rich":[76],"about":[78],"category":[81],"dynamics.":[83],"We":[84],"conducted":[85],"user":[87],"study":[88],"over":[90],"300":[91],"participants":[92],"using":[93],"an":[94],"online":[95],"crowdsourcing":[96],"service.":[97],"The":[98],"results":[99],"showed":[100],"that":[101],"words":[104],"could":[105],"only":[107],"effectively":[108],"naturally":[110],"dynamics":[113],"while":[116],"clarify":[117],"position":[119],"source,":[123],"but":[124],"also":[125],"contribute":[126],"making":[128],"watching":[130],"more":[131],"enjoyable":[132],"increasing":[134],"impact":[137],"video.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
