{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T17:03:32Z","timestamp":1776099812435,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":51,"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\/3663548.3688495","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T18:37:25Z","timestamp":1729449445000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Record, Transcribe, Share: An Accessible Open-Source Video Platform for Deaf and Hard of Hearing Viewers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1296-4987","authenticated-orcid":false,"given":"Korbinian","family":"Kuhn","sequence":"first","affiliation":[{"name":"Stuttgart Media University, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4618-376X","authenticated-orcid":false,"given":"Benedikt","family":"Reuter","sequence":"additional","affiliation":[{"name":"Stuttgart Media University, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9866-2175","authenticated-orcid":false,"given":"Niklas","family":"Egger","sequence":"additional","affiliation":[{"name":"Stuttgart Media University, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3129-1897","authenticated-orcid":false,"given":"Gottfried","family":"Zimmermann","sequence":"additional","affiliation":[{"name":"Stuttgart Media University, Germany"}]}],"member":"320","published-online":{"date-parts":[[2024,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376563"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517428.3544808"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78095-1_15"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517681"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3587281.3587286"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3641988"},{"key":"e_1_3_2_1_7_1","volume-title":"Advances in Neural Information Processing Systems, Hugo Larochelle, Marc\u2019Aurelio Ranzato, Raia Hadsell, Maria\u00a0Florina Balcan, and Hsuan-Tien Lin (Eds.). Vol.\u00a033. Curran Associates","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. In Advances in Neural Information Processing Systems, Hugo Larochelle, Marc\u2019Aurelio Ranzato, Raia Hadsell, Maria\u00a0Florina Balcan, and Hsuan-Tien Lin (Eds.). Vol.\u00a033. Curran Associates, Inc., virtual, 12449\u201312460. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/92d1e1eb1cd6f9fba3227870bb6d7f07-Paper.pdf"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-78"},{"key":"e_1_3_2_1_9_1","unstructured":"Lo\u00efc Barrault Yu-An Chung Mariano\u00a0Cora Meglioli David Dale Ning Dong Paul-Ambroise Duquenne Hady Elsahar Hongyu Gong Kevin Heffernan John Hoffman 2023. SeamlessM4T-Massively Multilingual & Multimodal Machine Translation. arxiv:2308.11596"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290607.3312921"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132525.3132541"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-105"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1353\/aad.2019.0002"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"e_1_3_2_1_15_1","unstructured":"William Chan Daniel Park Chris Lee Yu Zhang Quoc Le and Mohammad Norouzi. 2021. SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network. arxiv:2104.02133"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICALT.2017.11"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/FIE.2014.7044040"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"e_1_3_2_1_19_1","unstructured":"Sanchit Gandhi Patrick von Platen and Alexander\u00a0M. Rush. 2023. Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling. arxiv:2311.00430\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2311.00430"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3430263.3452435"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2513383.2513413"},{"key":"e_1_3_2_1_22_1","volume-title":"TED-LIUM 3: Twice as Much Data and Corpus Repartition for Experiments on Speaker Adaptation","author":"Hernandez Fran\u00e7ois","unstructured":"Fran\u00e7ois Hernandez, Vincent Nguyen, Sahar Ghannay, Natalia Tomashenko, and Yannick Est\u00e8ve. 2018. TED-LIUM 3: Twice as Much Data and Corpus Repartition for Experiments on Speaker Adaptation. In Speech and Computer, Alexey Karpov, Oliver Jokisch, and Rodmonga Potapova (Eds.). Springer International Publishing, Cham, 198\u2013208."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308561.3353781"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2982142.2982164"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517428.3550375"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3636513"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3585724"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2384916.2384930"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2543578"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2380116.2380122"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1279540.1279551"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.156"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific","author":"Mach\u00e1\u010dek Dominik","year":"2023","unstructured":"Dominik Mach\u00e1\u010dek, Raj Dabre, and Ond\u0159ej Bojar. 2023. Turning Whisper into Real-Time Transcription System. In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations, Sriparna Saha and Herry Sujaini (Eds.). Association for Computational Linguistics, Bali, Indonesia, 17\u201324. https:\/\/aclanthology.org\/2023.ijcnlp-demo.3"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3479578"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580809"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1357054.1357117"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373625.3418030"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2957276.2957310"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"e_1_3_2_1_42_1","volume-title":"Assistive Technology, Accessibility and (e)Inclusion: 18th International Conference, ICCHP-AAATE","author":"Piskorek Patricia","year":"2022","unstructured":"Patricia Piskorek, Nadine Sienel, Korbinian Kuhn, Verena Kersken, and Gottfried Zimmermann. 2022. Evaluating collaborative editing of ai-generated live subtitles by non-professionals in German university lectures. In Assistive Technology, Accessibility and (e)Inclusion: 18th International Conference, ICCHP-AAATE 2022, Lecco, Italy, July 11\u201315, 2022, Open Access Compendium, Part I. ICCHP, Lecco, Italy, 165\u2013175."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-205"},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0202)","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Tao Xu, Greg Brockman, Christine Mcleavey, and Ilya Sutskever. 2023. Robust Speech Recognition via Large-Scale Weak Supervision. In Proceedings of the 40th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, Honolulu, Hawaii, USA, 28492\u201328518. https:\/\/proceedings.mlr.press\/v202\/radford23a.html"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.9781\/ijimai.2017.09.001"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501843"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452918.3458792"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2016.7498924"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/11788713_100"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2982142.2982205"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.02.014"}],"event":{"name":"ASSETS '24: The 26th International ACM SIGACCESS Conference on Computers and Accessibility","location":"St. John's NL Canada","acronym":"ASSETS '24","sponsor":["SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["The 26th International ACM SIGACCESS Conference on Computers and Accessibility"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3663548.3688495","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\/3663548.3688495"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":51,"alternative-id":["10.1145\/3663548.3688495","10.1145\/3663548"],"URL":"https:\/\/doi.org\/10.1145\/3663548.3688495","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"}}]}}