{"id":"https://openalex.org/W2184040158","doi":"https://doi.org/10.21437/interspeech.2014-410","title":"Data-driven generation of text balloons based on linguistic and acoustic features of a comics-anime corpus","display_name":"Data-driven generation of text balloons based on linguistic and acoustic features of a comics-anime corpus","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2184040158","doi":"https://doi.org/10.21437/interspeech.2014-410","mag":"2184040158"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-410","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-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/A5051102142","display_name":"Sho Matsumiya","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sho Matsumiya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000692949","display_name":"Graham Neubig","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science & Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science & Technology#TAB#","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051102142"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3129,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.64180442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13155","display_name":"Digital Communication and Language","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T13155","display_name":"Digital Communication and Language","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9714000225067139,"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/comics","display_name":"Comics","score":0.7643610239028931},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.740253210067749},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6291255354881287},{"id":"https://openalex.org/keywords/anime","display_name":"Anime","score":0.6157724261283875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5562235116958618},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5061907172203064},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5038592219352722},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.47708138823509216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45919501781463623},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.43983006477355957},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4346265196800232},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3896790146827698},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.15479689836502075}],"concepts":[{"id":"https://openalex.org/C529099274","wikidata":"https://www.wikidata.org/wiki/Q1004","display_name":"Comics","level":2,"score":0.7643610239028931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.740253210067749},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6291255354881287},{"id":"https://openalex.org/C118130439","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Anime","level":2,"score":0.6157724261283875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5562235116958618},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5061907172203064},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5038592219352722},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.47708138823509216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45919501781463623},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.43983006477355957},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4346265196800232},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3896790146827698},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.15479689836502075},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2014-410","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W7527729","https://openalex.org/W28755848","https://openalex.org/W71705338","https://openalex.org/W129751587","https://openalex.org/W147964346","https://openalex.org/W165283731","https://openalex.org/W1501669607","https://openalex.org/W1503007957","https://openalex.org/W1967529845","https://openalex.org/W1991480454","https://openalex.org/W2033455467","https://openalex.org/W2043746194","https://openalex.org/W2085662862","https://openalex.org/W2092206588","https://openalex.org/W2098490501","https://openalex.org/W2099884129","https://openalex.org/W2109712306","https://openalex.org/W2130162821","https://openalex.org/W2141869026","https://openalex.org/W2156848952","https://openalex.org/W2171982660","https://openalex.org/W2432261168"],"related_works":["https://openalex.org/W4385571610","https://openalex.org/W4200068392","https://openalex.org/W4362498905","https://openalex.org/W2338806053","https://openalex.org/W2772686614","https://openalex.org/W2293738010","https://openalex.org/W2036933852","https://openalex.org/W1489621819","https://openalex.org/W2572044271","https://openalex.org/W2152945827"],"abstract_inverted_index":{"Most":[0],"automatic":[1],"speech":[2,34,99],"recognition":[3,32],"systems":[4,63],"existing":[5],"today":[6],"are":[7],"still":[8],"limited":[9],"to":[10,59,114,121,151],"recognizing":[11],"what":[12],"is":[13,22,58,140,149],"being":[14,17,23],"said,":[15],"without":[16],"concerned":[18],"with":[19,91,158],"how":[20,41],"it":[21],"said.":[24],"On":[25],"the":[26,116,147,153],"other":[27],"hand,":[28],"research":[29],"on":[30,128],"emotion":[31],"from":[33,68],"has":[35,50],"recently":[36],"gained":[37],"considerable":[38],"interest,":[39],"but":[40],"those":[42],"emotions":[43],"could":[44],"be":[45],"expressed":[46],"in":[47],"text-based":[48,83,101],"communication":[49,102],"not":[51],"been":[52],"widely":[53],"investigated.":[54],"Our":[55],"long-term":[56],"goal":[57],"construct":[60],"expressive":[61,138,165],"speech-to-text":[62],"that":[64,95,137],"conveys":[65],"all":[66],"information":[67],"acoustic":[69,125,170],"speech,":[70],"including":[71],"verbal":[72],"message,":[73],"emotional":[74,98],"state,":[75],"speaker":[76],"condition,":[77],"and":[78,124,131,146,169],"background":[79],"noise,":[80],"into":[81,100],"unified":[82],"communication.":[84],"In":[85],"this":[86],"preliminary":[87],"study,":[88],"we":[89,119],"start":[90],"developing":[92],"a":[93],"system":[94,148],"can":[96],"convey":[97],"by":[103],"way":[104],"of":[105,155],"text":[106,117,139,156,166],"balloons.":[107],"As":[108],"there":[109],"exist":[110],"many":[111],"possible":[112],"ways":[113],"generate":[115],"balloons,":[118],"propose":[120],"utilize":[122],"linguistic":[123,168],"features":[126,171],"based":[127],"comic":[129],"books":[130],"anime":[132],"films.":[133],"Experimental":[134],"results":[135],"reveal":[136],"more":[141],"preferable":[142],"than":[143],"static":[144],"text,":[145],"able":[150],"estimate":[152],"shape":[154],"balloons":[157],"87.01%":[159],"accuracy.":[160],"Index":[161],"Terms:":[162],"data-driven":[163],"approaches,":[164],"generation,":[167]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}