{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T10:57:51Z","timestamp":1781002671066,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772318.3790911","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:12:21Z","timestamp":1776053541000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Lost in Transcription: Subtitle Errors in Automatic Speech Recognition Reduce Speaker and Content Evaluations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1248-0385","authenticated-orcid":false,"given":"Kowe","family":"Kadoma","sequence":"first","affiliation":[{"name":"Information Science, Cornell University, Ithaca, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6694-289X","authenticated-orcid":false,"given":"Priyal","family":"Shrivastava","sequence":"additional","affiliation":[{"name":"Human-Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6436-3877","authenticated-orcid":false,"given":"Mor","family":"Naaman","sequence":"additional","affiliation":[{"name":"Cornell Tech, New York, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Tom Apone Marcia Brooks and Trisha O\u2019Connell. 2010. Caption Accuracy Metrics Project. Caption Viewer Survey: Error Ranking of Real-time Captions in Live Television News Programs."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3641988"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594058"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-318"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479897"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Wing\u00a0Shan Chan Jan-Louis Kruger and Stephen Doherty. 2019. Comparing the impact of automatically generated and corrected subtitles on cognitive load and learning in a first-and second-language educational context. Linguistica Antverpiensia New Series\u2013Themes in Translation Studies 18 (2019).","DOI":"10.52034\/lanstts.v18i0.506"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Jessica Chandras. 2020. Multilingualismin India. Education about Asia 25 3 (2020).","DOI":"10.65959\/eaa.1666"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"James\u00a0M Clark and Allan Paivio. 1991. Dual coding theory and education. Educational psychology review 3 3 (1991) 149\u2013210.","DOI":"10.1007\/BF01320076"},{"key":"e_1_3_3_2_10_2","unstructured":"American\u00a0Immigration Council. 2022. https:\/\/www.americanimmigrationcouncil.org\/fact-sheet\/foreign-born-stem-workers-united-states\/"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.21437\/AVSP.2017-12"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.761"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2820766"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713622"},{"key":"e_1_3_3_2_15_2","unstructured":"English Broadcasters\u00a0Group (EBG). 2014. Report on Efforts to Improve the Quality of Closed Captioning."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714059"},{"key":"e_1_3_3_2_17_2","unstructured":"National\u00a0Science Foundation. 2024. https:\/\/ncses.nsf.gov\/pubs\/nsb20245"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"Batya Friedman and Helen Nissenbaum. 1996. Bias in computer systems. ACM Trans. Inf. Syst. 14 3 (July 1996) 330\u2013347. 10.1145\/230538.230561","DOI":"10.1145\/230538.230561"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Jairo\u00a0N Fuertes William\u00a0H Gottdiener Helena Martin Tracey\u00a0C Gilbert and Howard Giles. 2012. A meta-analysis of the effects of speakers\u2019 accents on interpersonal evaluations. European journal of social psychology 42 1 (2012) 120\u2013133.","DOI":"10.1002\/ejsp.862"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"MA Gernsbacher. 2015. Video captions benefit everyone. Policy Insights from the Behavioral and Brain Sciences 2 (1) 195-202.","DOI":"10.1177\/2372732215602130"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Agata Gluszek and John\u00a0F Dovidio. 2010. The way they speak: A social psychological perspective on the stigma of nonnative accents in communication. Personality and social psychology review 14 2 (2010) 214\u2013237.","DOI":"10.1177\/1088868309359288"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-48309-7_5"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501995"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.890"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Louis Hickman Markus Langer Rachel\u00a0M Saef and Louis Tay. 2024. Automated speech recognition bias in personnel selection: The case of automatically scored job interviews. Journal of Applied Psychology (2024).","DOI":"10.1037\/apl0001247"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533089"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290607.3312915"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","unstructured":"Seoyoung Kim Yeon\u00a0Su Park Dakyeom Ahn Jin\u00a0Myung Kwak and Juho Kim. 2024. Is the Same Performance Really the Same?: Understanding How Listeners Perceive ASR Results Differently According to the Speaker\u2019s Accent. Proc. ACM Hum.-Comput. Interact. 8 CSCW1 Article 169 (April 2024) 22\u00a0pages. 10.1145\/3641008","DOI":"10.1145\/3641008"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","unstructured":"Allison Koenecke Andrew Nam Emily Lake Joe Nudell Minnie Quartey Zion Mengesha Connor Toups John\u00a0R. Rickford Dan Jurafsky and Sharad Goel. 2020. Racial disparities in automated speech recognition. Proceedings of the National Academy of Sciences 117 14 (2020) 7684\u20137689. arXiv:https:\/\/www.pnas.org\/doi\/pdf\/10.1073\/pnas.191576811710.1073\/pnas.1915768117","DOI":"10.1073\/pnas.1915768117"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/2509315.2509331"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","unstructured":"Korbinian Kuhn Verena Kersken Benedikt Reuter Niklas Egger and Gottfried Zimmermann. 2024. Measuring the Accuracy of Automatic Speech Recognition Solutions. ACM Trans. Access. Comput. 16 4 Article 25 (Jan. 2024) 23\u00a0pages. 10.1145\/3636513","DOI":"10.1145\/3636513"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/2700648.2809843"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Shiri Lev-Ari and Boaz Keysar. 2010. Why don\u2019t we believe non-native speakers? The influence of accent on credibility. Journal of experimental social psychology 46 6 (2010) 1093\u20131096.","DOI":"10.1016\/j.jesp.2010.05.025"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713124"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Tianyun Li and Agnieszka Chmiel. 2024. Automatic subtitles increase accuracy and decrease cognitive load in simultaneous interpreting. Interpreting 26 2 (2024) 253\u2013281.","DOI":"10.1075\/intp.00111.li"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308560.3317597"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","unstructured":"Tingting Liu and Vahid Aryadoust. 2024. Orchestrating Teacher Peer and Self-Feedback to Enhance Learners\u2019 Cognitive Behavioral and Emotional Engagement and Public Speaking Competence. Behavioral Sciences 14 8 (2024). 10.3390\/bs14080725","DOI":"10.3390\/bs14080725"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Anna Lorenzoni Rita Faccio and Eduardo Navarrete. 2024. Does foreign-accented speech affect credibility? Evidence from the illusory-truth paradigm. Journal of Cognition 7 1 (2024) 26.","DOI":"10.5334\/joc.353"},{"key":"e_1_3_3_2_39_2","first-page":"21","volume-title":"Speech-to-speech translation","author":"Lu Xugang","year":"2019","unstructured":"Xugang Lu, Sheng Li, and Masakiyo Fujimoto. 2019. Automatic speech recognition. In Speech-to-speech translation. Springer, 21\u201338."},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Zion Mengesha Courtney Heldreth Michal Lahav Juliana Sublewski and Elyse Tuennerman. 2021. \"I don\u2019t think these devices are very culturally sensitive.\" - The impact of errors on African Americans in Automated Speech Recognition. Frontiers in Artificial Intelligence 26 (2021). https:\/\/www.frontiersin.org\/journals\/artificial-intelligence\/articles\/10.3389\/frai.2021.725911","DOI":"10.3389\/frai.2021.725911"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732018"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Mila Mileva and Nadine Lavan. 2023. Trait impressions from voices are formed rapidly within 400 ms of exposure. Journal of Experimental Psychology: General 152 6 (2023) 1539.","DOI":"10.1037\/xge0001325"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-364"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"crossref","unstructured":"Nora\u00a0A Murphy and Judith\u00a0A Hall. 2021. Capturing behavior in small doses: A review of comparative research in evaluating thin slices for behavioral measurement. Frontiers in psychology 12 (2021) 667326.","DOI":"10.3389\/fpsyg.2021.667326"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21707-4_30"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"crossref","unstructured":"Jan Pedersen. 2017. The FAR model: assessing quality in interlingual subtitling. Jostrans: The Journal of Specialised Translation28 (2017) 210\u2013229.","DOI":"10.26034\/cm.jostrans.2017.239"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","unstructured":"Pablo Romero-Fresco. 2016. Accessing communication: The quality of live subtitles in the UK. Language & Communication 49 (2016) 56\u201369. 10.1016\/j.langcom.2016.06.001","DOI":"10.1016\/j.langcom.2016.06.001"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Pablo Romero-Fresco and Nazaret Fresno. 2023. The accuracy of automatic and human live captions in English. Linguistica Antverpiensia New Series\u2013Themes in Translation Studies 22 (2023).","DOI":"10.52034\/lans-tts.v22i.774"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"crossref","unstructured":"Pablo Romero-Fresco and Yanou Van\u00a0Gauwbergen. 2025. Fit for What Purpose? NER Certification of Automatic Captions in English and Spanish. Applied Sciences 15 3 (2025) 1387.","DOI":"10.3390\/app15031387"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604673"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/1841853.1841865"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.602"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Jessica\u00a0L Spence Matthew\u00a0J Hornsey Eloise\u00a0M Stephenson and Kana Imuta. 2024. Is your accent right for the job? A meta-analysis on accent bias in hiring decisions. Personality and Social Psychology Bulletin 50 3 (2024) 371\u2013386.","DOI":"10.1177\/01461672221130595"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"crossref","unstructured":"Kamal\u00a0K Sridhar. 1996. Language in education: Minorities and multilingualism in India. International Review of Education 42 4 (1996) 327\u2013347.","DOI":"10.1007\/BF00601095"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3465416.3483305"},{"key":"e_1_3_3_2_56_2","unstructured":"Gabriel Synnaeve Qiantong Xu Jacob Kahn Tatiana Likhomanenko Edouard Grave Vineel Pratap Anuroop Sriram Vitaliy Liptchinsky and Ronan Collobert. 2020. End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures. arxiv:https:\/\/arXiv.org\/abs\/1911.08460\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1911.08460"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","unstructured":"Agnieszka Szarkowska Valentina Ragni Sonia Szkriba Sharon Black Jan-Louis Kruger and David Orrego-Carmona. 2024. \u2018That\u2019s not what they said!\u2019 The impact of incongruities between the dialogue and intralingual subtitles on viewer experience. Perspectives 0 0 (2024) 1\u201320. arXiv:10.1080\/0907676X.2024.2386040","DOI":"10.1080\/0907676X.2024.2386040"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1746"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"crossref","unstructured":"Gregory Taylor. 2005. Perceived processing strategies of students watching captioned video. Foreign Language Annals 38 3 (2005) 422\u2013427.","DOI":"10.1111\/j.1944-9720.2005.tb02228.x"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"crossref","unstructured":"Roli Varma. 2010. India-born in the US science and engineering workforce. American Behavioral Scientist 53 7 (2010) 1064\u20131078.","DOI":"10.1177\/0002764209356239"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"crossref","unstructured":"Luuk Waes Mari\u00eblle Leijten and Aline Remael. 2013. Live subtitling with speech recognition. Causes and consequences of text reduction. Across languages and cultures 14 1 (2013) 15\u201346.","DOI":"10.1556\/Acr.14.2013.1.2"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533088"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581357"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642900"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.iwslt-1.1"}],"event":{"name":"CHI 2026: CHI Conference on Human Factors in Computing Systems","location":"Barcelona Spain","acronym":"CHI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772318.3790911","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T10:05:51Z","timestamp":1780999551000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3790911"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":64,"alternative-id":["10.1145\/3772318.3790911","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3790911","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}