{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T16:49:11Z","timestamp":1764175751108,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,27]]},"DOI":"10.1145\/3663548.3688494","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T18:37:25Z","timestamp":1729449445000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["CARTGPT: Improving CART Captioning using Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3081-1134","authenticated-orcid":false,"given":"Liang-Yuan","family":"Wu","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, University of Michigan, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6285-6116","authenticated-orcid":false,"given":"Andrea","family":"Kleiver","sequence":"additional","affiliation":[{"name":"Certified CART Captioner, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6176-968X","authenticated-orcid":false,"given":"Dhruv","family":"Jain","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of Michigan, United States"}]}],"member":"320","published-online":{"date-parts":[[2024,10,27]]},"reference":[{"volume-title":"Closed captioning: Subtitling, stenography, and the digital convergence of text with television","author":"Downey Gregory J","key":"e_1_3_2_1_1_1","unstructured":"Gregory J Downey. 2008. Closed captioning: Subtitling, stenography, and the digital convergence of text with television. JHU Press."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01423-1"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCI.2016.7732361"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1640377.1640384"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458754"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2513383.2513413"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"volume-title":"Content analysis: An introduction to its methodology","author":"Krippendorff Klaus","key":"e_1_3_2_1_8_1","unstructured":"Klaus Krippendorff. 2018. Content analysis: An introduction to its methodology. Sage publications."},{"key":"e_1_3_2_1_9_1","unstructured":"Judy Larson and others. 1999. CART (Communication Access Realtime Translation). PEPNet Tipsheet. PEPNet-Northeast."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461121.2461151"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"e_1_3_2_1_12_1","unstructured":"Rao Ma Mengjie Qian Potsawee Manakul Mark Gales and Kate Knill. 2023. Can Generative Large Language Models Perform ASR Error Correction? arXiv preprint arXiv:2307.04172."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Andrew Maas Quoc V Le Tyler M O'neil Oriol Vinyals Patrick Nguyen and Andrew Y Ng. 2012. Recurrent neural networks for noise reduction in robust ASR. INTERSPEECH.","DOI":"10.21437\/Interspeech.2012-6"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apergo.2023.104094"},{"key":"e_1_3_2_1_15_1","volume-title":"Communication Access Realtime Translation. Retrieved","author":"National Association of the Deaf (NAD).","year":"2018","unstructured":"National Association of the Deaf (NAD). Communication Access Realtime Translation. Retrieved April 7, 2018 from https:\/\/www.nad.org\/resources\/technology\/captioning-for-access\/communication-access-realtime-translation\/"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"e_1_3_2_1_17_1","volume-title":"Mls: A large-scale multilingual dataset for speech research. arXiv preprint arXiv:2012.03411.","author":"Pratap Vineel","year":"2020","unstructured":"Vineel Pratap, Qiantong Xu, Anuroop Sriram, Gabriel Synnaeve, and Ronan Collobert. 2020. Mls: A large-scale multilingual dataset for speech research. arXiv preprint arXiv:2012.03411."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Gonzalo Ramos Christopher Meek Patrice Simard Jina Suh and Soroush Ghorashi. 2020. Interactive machine teaching: a human-centered approach to building machine-learned models. Human\u2013Computer Interaction 35 5\u20136: 413\u2013451.","DOI":"10.1080\/07370024.2020.1734931"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3451760"},{"key":"e_1_3_2_1_20_1","unstructured":"Rohan Taori Ishaan Gulrajani Tianyi Zhang Yann Dubois Xuechen Li Carlos Guestrin Percy Liang and Tatsunori B Hashimoto. 2023. Stanford alpaca: An instruction-following llama model. Retrieved from https:\/\/crfm.stanford.edu\/2023\/03\/13\/alpaca.html"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.3390\/sym11081018"},{"key":"e_1_3_2_1_22_1","unstructured":"Yue Zhang Leyang Cui Deng Cai Xinting Huang Tao Fang and Wei Bi. 2023. Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance. arXiv preprint arXiv:2305.13225."},{"key":"e_1_3_2_1_23_1","volume-title":"Retrieved","author":"What","year":"2022","unstructured":"What is real-time captioning? | UW DO-IT. Retrieved August 12, 2022 from https:\/\/www.washington.edu\/doit\/what-real-time-captioning#:\u223c:text=Captions%2C composed of text%2C are,as an event takes place."},{"key":"e_1_3_2_1_24_1","volume-title":"Retrieved","author":"Captions","year":"2023","unstructured":"Captions: Humans vs Artificial Intelligence: Who Wins? | Equal Entry. Retrieved September 14, 2023 from https:\/\/equalentry.com\/caption-videos-human-vs-automatic-captions\/"},{"key":"e_1_3_2_1_25_1","unstructured":"Live Professional Captions vs. CART Captioning. Retrieved September 14 2023 from https:\/\/www.3playmedia.com\/blog\/live-professional-captions-vs-cart-captioning-whats-the-difference\/"},{"key":"e_1_3_2_1_26_1","unstructured":"GPT-4 | OpenAI. Retrieved July 2 2024 from https:\/\/openai.com\/index\/gpt-4\/"},{"key":"e_1_3_2_1_27_1","unstructured":"Introducing Whisper | OpenAI. Retrieved July 2 2024 from https:\/\/openai.com\/index\/whisper\/"},{"key":"e_1_3_2_1_28_1","unstructured":"MIT OpenCourseWare | Free Online Course Materials. Retrieved September 13 2023 from https:\/\/ocw.mit.edu\/"},{"volume-title":"2023 from https:\/\/catalog.ldc.upenn.edu\/LDC97S42","author":"CALLHOME American English Speech - Linguistic Data Consortium","key":"e_1_3_2_1_29_1","unstructured":"CALLHOME American English Speech - Linguistic Data Consortium. Retrieved September 13, 2023 from https:\/\/catalog.ldc.upenn.edu\/LDC97S42"}],"event":{"name":"ASSETS '24: The 26th International ACM SIGACCESS Conference on Computers and Accessibility","sponsor":["SIGACCESS ACM Special Interest Group on Accessible Computing"],"location":"St. John's NL Canada","acronym":"ASSETS '24"},"container-title":["The 26th International ACM SIGACCESS Conference on Computers and Accessibility"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3663548.3688494","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:57:17Z","timestamp":1750291037000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3663548.3688494"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":29,"alternative-id":["10.1145\/3663548.3688494","10.1145\/3663548"],"URL":"https:\/\/doi.org\/10.1145\/3663548.3688494","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]},"assertion":[{"value":"2024-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}