{"id":"https://openalex.org/W2525932717","doi":"https://doi.org/10.1109/tmm.2016.2613641","title":"Visualizing Video Sounds With Sound Word Animation to Enrich User Experience","display_name":"Visualizing Video Sounds With Sound Word Animation to Enrich User Experience","publication_year":2016,"publication_date":"2016-09-26","ids":{"openalex":"https://openalex.org/W2525932717","doi":"https://doi.org/10.1109/tmm.2016.2613641","mag":"2525932717"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2016.2613641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2016.2613641","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5088412694","display_name":"Fangzhou Wang","orcid":"https://orcid.org/0000-0002-9640-5285"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Fangzhou Wang","raw_affiliation_strings":["Google, Inc. Mountain View, CA, USA","University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc. Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"University of Tokyo, 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, Atsugi-shi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Atsugi-shi, Japan","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, Atsugi-shi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Atsugi-shi, Japan","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":["University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0009,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.92335105,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"19","issue":"2","first_page":"418","last_page":"429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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":0.996999979019165,"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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9929999709129333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8382111191749573},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.6203929781913757},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6132485270500183},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6092422008514404},{"id":"https://openalex.org/keywords/nonverbal-communication","display_name":"Nonverbal communication","score":0.5198793411254883},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4900461435317993},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3663366436958313},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.36275380849838257},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2689236104488373},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1388213336467743},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.13169240951538086},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.10649806261062622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8382111191749573},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.6203929781913757},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6132485270500183},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6092422008514404},{"id":"https://openalex.org/C145633318","wikidata":"https://www.wikidata.org/wiki/Q207125","display_name":"Nonverbal communication","level":2,"score":0.5198793411254883},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4900461435317993},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3663366436958313},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.36275380849838257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2689236104488373},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1388213336467743},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.13169240951538086},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.10649806261062622},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/tmm.2016.2613641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2016.2613641","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W57010538","https://openalex.org/W77111623","https://openalex.org/W1503007957","https://openalex.org/W1510526001","https://openalex.org/W1555152292","https://openalex.org/W1567619397","https://openalex.org/W1580529010","https://openalex.org/W1910610070","https://openalex.org/W1968589407","https://openalex.org/W1971495865","https://openalex.org/W2005136695","https://openalex.org/W2030371206","https://openalex.org/W2035140157","https://openalex.org/W2035761357","https://openalex.org/W2039920533","https://openalex.org/W2050968192","https://openalex.org/W2074188409","https://openalex.org/W2086384421","https://openalex.org/W2103568877","https://openalex.org/W2104298926","https://openalex.org/W2116681922","https://openalex.org/W2122532446","https://openalex.org/W2123737024","https://openalex.org/W2126532873","https://openalex.org/W2128272608","https://openalex.org/W2130640900","https://openalex.org/W2147853020","https://openalex.org/W2151401338","https://openalex.org/W2153635508","https://openalex.org/W2156468046","https://openalex.org/W2164084182","https://openalex.org/W2165713459","https://openalex.org/W2168356304","https://openalex.org/W2183182206","https://openalex.org/W2188210106","https://openalex.org/W2313745396","https://openalex.org/W2403373496","https://openalex.org/W4253161066","https://openalex.org/W4361983081","https://openalex.org/W6602326871","https://openalex.org/W6603105407","https://openalex.org/W6630424276","https://openalex.org/W6633908967"],"related_works":["https://openalex.org/W2391422698","https://openalex.org/W52595306","https://openalex.org/W2385209118","https://openalex.org/W4299362043","https://openalex.org/W1522611117","https://openalex.org/W4236235619","https://openalex.org/W4312974229","https://openalex.org/W4310844315","https://openalex.org/W2354814076","https://openalex.org/W2570142844"],"abstract_inverted_index":{"Sound":[0],"information":[1,83],"in":[2,8,18,68],"videos":[3],"plays":[4],"an":[5,107,120],"important":[6],"role":[7],"shaping":[9],"the":[10,64,69,85,93,102,127,132,141,147,150,164],"user":[11,103,113,128],"experience.":[12],"When":[13],"sound":[14,24,58,65,86,95,134,144,151],"is":[15],"not":[16,31],"accessible":[17],"videos,":[19],"text":[20,28],"captions":[21,29],"can":[22,136],"provide":[23],"information.":[25],"However,":[26],"conventional":[27],"are":[30,39],"very":[32],"expressive":[33],"for":[34,71],"nonverbal":[35,53,79],"sounds":[36,55,80],"because":[37],"they":[38],"designed":[40],"to":[41,50,157],"visualize":[42,140],"speech":[43],"sounds.":[44],"Here,":[45],"we":[46,105],"present":[47],"a":[48,112],"framework":[49,100],"automatically":[51],"transform":[52],"video":[54,70],"into":[56],"animated":[57,94,133],"words":[59,96,135],"and":[60,88,110,138,162],"position":[61,148],"them":[62],"near":[63],"source":[66,152],"objects":[67],"visualization.":[72],"This":[73],"provides":[74],"natural":[75],"visual":[76,165],"representation":[77],"of":[78,126,143,149,167],"with":[81],"rich":[82],"about":[84],"category":[87],"dynamics.":[89],"To":[90],"evaluate":[91],"how":[92],"generated":[97],"by":[98],"our":[99],"affect":[101],"experience,":[104],"implemented":[106],"experimental":[108],"system":[109],"conducted":[111],"study":[114,129],"involving":[115],"over":[116],"300":[117],"participants":[118],"from":[119],"online":[121],"crowdsourcing":[122],"service.":[123],"The":[124],"results":[125],"show":[130],"that":[131],"effectively":[137],"naturally":[139],"dynamics":[142],"while":[145],"clarifying":[146],"as":[153,155],"well":[154],"contribute":[156],"making":[158],"video-watching":[159],"more":[160],"enjoyable":[161],"increasing":[163],"impact":[166],"videos.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}