{"id":"https://openalex.org/W4396832409","doi":"https://doi.org/10.1145/3613904.3642162","title":"Unspoken Sound: Identifying Trends in Non-Speech Audio Captioning on YouTube","display_name":"Unspoken Sound: Identifying Trends in Non-Speech Audio Captioning on YouTube","publication_year":2024,"publication_date":"2024-05-11","ids":{"openalex":"https://openalex.org/W4396832409","doi":"https://doi.org/10.1145/3613904.3642162"},"language":"en","primary_location":{"id":"doi:10.1145/3613904.3642162","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642162","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642162","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642162","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069235453","display_name":"Lloyd May","orcid":"https://orcid.org/0000-0003-4692-8261"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lloyd May","raw_affiliation_strings":["Center for Computer Research in Music and Acoustics (CCRMA), Stanford University, United States"],"raw_orcid":"https://orcid.org/0000-0003-4692-8261","affiliations":[{"raw_affiliation_string":"Center for Computer Research in Music and Acoustics (CCRMA), Stanford University, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031965299","display_name":"Keita Ohshiro","orcid":"https://orcid.org/0000-0001-8612-1898"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keita Ohshiro","raw_affiliation_strings":["Department of Informatics, New Jersey Institute of Technology, United States"],"raw_orcid":"https://orcid.org/0000-0001-8612-1898","affiliations":[{"raw_affiliation_string":"Department of Informatics, New Jersey Institute of Technology, United States","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040254449","display_name":"Khang Dang","orcid":"https://orcid.org/0000-0003-3481-497X"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khang Dang","raw_affiliation_strings":["Informatics, New Jersey Institute of Technology, United States"],"raw_orcid":"https://orcid.org/0000-0003-3481-497X","affiliations":[{"raw_affiliation_string":"Informatics, New Jersey Institute of Technology, United States","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011188265","display_name":"Sripathi Sridhar","orcid":"https://orcid.org/0000-0001-9761-3564"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sripathi Sridhar","raw_affiliation_strings":["Sound Interaction and Computing Lab, New Jersey Institute of Technology, United States"],"raw_orcid":"https://orcid.org/0000-0001-9761-3564","affiliations":[{"raw_affiliation_string":"Sound Interaction and Computing Lab, New Jersey Institute of Technology, United States","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035094450","display_name":"Jhanvi Pai","orcid":"https://orcid.org/0009-0004-6616-2579"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jhanvi Pai","raw_affiliation_strings":["Sound Interaction and Computing Lab, New Jersey Institute of Technology, United States"],"raw_orcid":"https://orcid.org/0009-0004-6616-2579","affiliations":[{"raw_affiliation_string":"Sound Interaction and Computing Lab, New Jersey Institute of Technology, United States","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021235229","display_name":"Magdalena Fuentes","orcid":"https://orcid.org/0000-0003-4506-6639"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Magdalena Fuentes","raw_affiliation_strings":["MARL-IDM, New York University, United States"],"raw_orcid":"https://orcid.org/0000-0003-4506-6639","affiliations":[{"raw_affiliation_string":"MARL-IDM, New York University, United States","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100626494","display_name":"Sooyeon Lee","orcid":"https://orcid.org/0000-0002-4971-2004"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sooyeon Lee","raw_affiliation_strings":["Informatics/Ying Wu College of Computing, New Jersey Institute of Technology, United States"],"raw_orcid":"https://orcid.org/0000-0002-4971-2004","affiliations":[{"raw_affiliation_string":"Informatics/Ying Wu College of Computing, New Jersey Institute of Technology, United States","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056532548","display_name":"Mark Cartwright","orcid":"https://orcid.org/0000-0002-5908-390X"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Cartwright","raw_affiliation_strings":["New York University, United States"],"raw_orcid":"https://orcid.org/0000-0002-5908-390X","affiliations":[{"raw_affiliation_string":"New York University, United States","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":27.9631,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.9925763,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9878000020980835,"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":0.9703999757766724,"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":0.9569118022918701},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.7573227882385254},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7112957835197449},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4102601110935211},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3937050402164459},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2507706880569458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15894591808319092}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9569118022918701},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.7573227882385254},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7112957835197449},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4102601110935211},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3937050402164459},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2507706880569458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15894591808319092},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3613904.3642162","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642162","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642162","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3613904.3642162","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642162","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642162","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396832409.pdf"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W264645860","https://openalex.org/W1554685869","https://openalex.org/W1600530438","https://openalex.org/W2008599024","https://openalex.org/W2029848040","https://openalex.org/W2049684864","https://openalex.org/W2072271845","https://openalex.org/W2086413085","https://openalex.org/W2117948609","https://openalex.org/W2128213565","https://openalex.org/W2163986367","https://openalex.org/W2325180458","https://openalex.org/W2336188181","https://openalex.org/W2338012757","https://openalex.org/W2525932717","https://openalex.org/W2533816498","https://openalex.org/W2535013011","https://openalex.org/W2769509476","https://openalex.org/W2799915114","https://openalex.org/W2897588549","https://openalex.org/W2940523565","https://openalex.org/W2943167538","https://openalex.org/W2952698673","https://openalex.org/W2964213897","https://openalex.org/W3007450755","https://openalex.org/W3031700288","https://openalex.org/W3094385957","https://openalex.org/W3157703700","https://openalex.org/W3165614589","https://openalex.org/W3186890588","https://openalex.org/W4221135284","https://openalex.org/W4224991981","https://openalex.org/W4253029038","https://openalex.org/W4307137011","https://openalex.org/W4322759491","https://openalex.org/W4366527514","https://openalex.org/W4366547608","https://openalex.org/W4366588062","https://openalex.org/W4387793540","https://openalex.org/W4387793730"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403"],"abstract_inverted_index":{"High-quality":[0],"closed":[1],"captioning":[2,39,112],"of":[3,14,24,52,75,88,108,121,124,146],"both":[4],"speech":[5,69],"and":[6,16,30,42,105,118,136],"non-speech":[7,90,109],"elements":[8],"(e.g.,":[9],"music,":[10],"sound":[11],"effects,":[12],"manner":[13],"speaking,":[15],"speaker":[17],"identification)":[18],"is":[19],"essential":[20],"for":[21,28,40,48,96,139],"the":[22,49,57,73,80,86,103,116,144],"accessibility":[23,145],"video":[25,54,148],"content,":[26,55],"especially":[27],"d/Deaf":[29],"hard-of-hearing":[31],"individuals.":[32],"While":[33],"many":[34,89],"regions":[35],"have":[36,71],"regulations":[37],"mandating":[38],"television":[41],"movies,":[43],"a":[44,122],"regulatory":[45],"gap":[46],"remains":[47],"vast":[50],"amount":[51],"web-based":[53],"including":[56,85],"staggering":[58],"500+":[59],"hours":[60],"uploaded":[61],"to":[62,142],"YouTube":[63,114],"every":[64],"minute.":[65],"Advances":[66],"in":[67],"automatic":[68],"recognition":[70],"bolstered":[72],"presence":[74],"captions":[76],"on":[77,113],"YouTube.":[78],"However,":[79],"technology":[81],"has":[82],"notable":[83],"limitations,":[84],"omission":[87],"elements,":[91],"which":[92],"are":[93],"often":[94],"crucial":[95],"understanding":[97],"content":[98],"narratives.":[99],"This":[100],"paper":[101],"examines":[102],"contemporary":[104],"historical":[106],"state":[107],"information":[110],"(NSI)":[111],"through":[115],"creation":[117],"exploratory":[119],"analysis":[120],"dataset":[123],"over":[125],"715k":[126],"videos.":[127],"We":[128],"identify":[129],"factors":[130],"that":[131],"influence":[132],"NSI":[133],"caption":[134],"practices":[135],"suggest":[137],"avenues":[138],"future":[140],"research":[141],"enhance":[143],"online":[147],"content.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}