{"id":"https://openalex.org/W4307137011","doi":"https://doi.org/10.1145/3517428.3544808","title":"Beyond Subtitles: Captioning and Visualizing Non-speech Sounds to Improve Accessibility of User-Generated Videos","display_name":"Beyond Subtitles: Captioning and Visualizing Non-speech Sounds to Improve Accessibility of User-Generated Videos","publication_year":2022,"publication_date":"2022-10-22","ids":{"openalex":"https://openalex.org/W4307137011","doi":"https://doi.org/10.1145/3517428.3544808"},"language":"en","primary_location":{"id":"doi:10.1145/3517428.3544808","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3517428.3544808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International ACM SIGACCESS Conference on Computers and Accessibility","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/A5024401317","display_name":"Oliver Alonzo","orcid":"https://orcid.org/0000-0001-9241-3117"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Oliver Alonzo","raw_affiliation_strings":["Rochester Institute of Technology, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, United States","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037455703","display_name":"Hijung Valentina Shin","orcid":"https://orcid.org/0000-0001-8798-4580"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hijung Valentina Shin","raw_affiliation_strings":["Adobe Research, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, United States","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038972102","display_name":"Dingzeyu Li","orcid":"https://orcid.org/0000-0002-4222-8105"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dingzeyu Li","raw_affiliation_strings":["Adobe Research, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, United States","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024401317"],"corresponding_institution_ids":["https://openalex.org/I155173764"],"apc_list":null,"apc_paid":null,"fwci":27.72,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.99656442,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9459999799728394,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9412999749183655,"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/closed-captioning","display_name":"Closed captioning","score":0.9544249176979065},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8343563079833984},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5583133697509766},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42757365107536316},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41040247678756714},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4031771421432495},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3331683874130249},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2902740240097046},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10963460803031921}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9544249176979065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8343563079833984},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5583133697509766},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42757365107536316},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41040247678756714},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4031771421432495},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3331683874130249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2902740240097046},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10963460803031921}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3517428.3544808","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3517428.3544808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International ACM SIGACCESS Conference on Computers and Accessibility","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1495425814","https://openalex.org/W1979290264","https://openalex.org/W1986827136","https://openalex.org/W2008599024","https://openalex.org/W2042531738","https://openalex.org/W2043594280","https://openalex.org/W2049684864","https://openalex.org/W2072271845","https://openalex.org/W2117948609","https://openalex.org/W2313096401","https://openalex.org/W2338012757","https://openalex.org/W2539062311","https://openalex.org/W2613250014","https://openalex.org/W2621608564","https://openalex.org/W2735180670","https://openalex.org/W2793846782","https://openalex.org/W2796199965","https://openalex.org/W2897588549","https://openalex.org/W2940523565","https://openalex.org/W2941163248","https://openalex.org/W2943167538","https://openalex.org/W3022725711","https://openalex.org/W3094550259","https://openalex.org/W3157703700","https://openalex.org/W3174259008"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Captioning":[0],"provides":[1],"access":[2],"to":[3,33,42,159],"sounds":[4,71,126],"in":[5,19,23,72,122,128,162],"audio-visual":[6],"content":[7,18],"for":[8,95,135,156],"people":[9],"who":[10],"are":[11],"Deaf":[12],"or":[13,78],"Hard-of-hearing":[14],"(DHH).":[15],"As":[16],"user-generated":[17,73],"online":[20,74],"videos":[21,75],"grows":[22],"prevalence,":[24],"researchers":[25],"have":[26],"explored":[27],"using":[28,76,101],"automatic":[29,102,157],"speech":[30],"recognition":[31],"(ASR)":[32],"automate":[34],"captioning.":[35],"However,":[36],"definitions":[37],"of":[38,91,141,146],"captions":[39,100,145],"(as":[40],"compared":[41],"subtitles)":[43],"include":[44,117,152],"non-speech":[45,70,125,147,164],"sounds,":[46],"which":[47,106],"ASR":[48],"typically":[49],"does":[50],"not":[51],"capture":[52],"as":[53,130,132],"it":[54],"focuses":[55],"on":[56,68],"speech.":[57],"Thus,":[58],"we":[59],"explore":[60],"DHH":[61,84,119],"viewers\u2019":[62,120],"and":[63,89,98,138],"hearing":[64,112,153],"video":[65,113],"creators\u2019":[66,154],"perspectives":[67],"captioning":[69,163],"text":[77],"graphics.":[79],"Formative":[80],"interviews":[81],"with":[82,110],"11":[83],"participants":[85],"informed":[86],"the":[87,139],"design":[88],"implementation":[90],"a":[92],"prototype":[93],"interface":[94],"authoring":[96],"text-based":[97,142],"graphic":[99,144],"sound":[103,136],"event":[104],"detection,":[105],"was":[107],"then":[108],"evaluated":[109],"10":[111],"creators.":[114],"Our":[115,149],"findings":[116,150],"identifying":[118],"interests":[121],"having":[123],"important":[124],"included":[127],"captions,":[129],"well":[131],"various":[133],"criteria":[134],"selection":[137],"appropriateness":[140],"versus":[143],"sounds.":[148,165],"also":[151],"requirements":[155],"tools":[158],"assist":[160],"them":[161]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}