{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:01:37Z","timestamp":1776931297802,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","funder":[{"name":"National Institutes of Health (NIH)","award":["R01EY034562"],"award-info":[{"award-number":["R01EY034562"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,26]]},"DOI":"10.1145\/3663547.3746320","type":"proceedings-article","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T16:33:49Z","timestamp":1761150829000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["DescribePro: Collaborative Audio Description with Human-AI Interaction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0556-8029","authenticated-orcid":false,"given":"Maryam S","family":"Cheema","sequence":"first","affiliation":[{"name":"Arizona State University, Tempe, Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7251-6661","authenticated-orcid":false,"given":"Sina","family":"Elahimanesh","sequence":"additional","affiliation":[{"name":"Sharif University of Technology, Tehran, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8544-2144","authenticated-orcid":false,"given":"Samuel","family":"Martin","sequence":"additional","affiliation":[{"name":"Arizona State University, Tempe, Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2625-8216","authenticated-orcid":false,"given":"Pooyan","family":"Fazli","sequence":"additional","affiliation":[{"name":"Arizona State University, Tempe, Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6437-0463","authenticated-orcid":false,"given":"Hasti","family":"Seifi","sequence":"additional","affiliation":[{"name":"Arizona State University, Tempe, Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,22]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"3Play Media. 2024. Audio Description: What It Is and How It Works. https:\/\/www.3playmedia.com\/learn\/popular-topics\/audio-description\/."},{"key":"e_1_3_3_2_3_2","unstructured":"Accessible Media Inc.2025. Post Production Described Video (DV). https:\/\/www.ami.ca\/described-video-dv"},{"key":"e_1_3_3_2_4_2","unstructured":"Inc. Audible\u00a0Sight. 2024. Audible Sight: A new method for creating audio descriptions. https:\/\/www.audiblesight.ai\/."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Aaron Bangor Philip\u00a0T Kortum and James\u00a0T Miller. 2008. An empirical evaluation of the system usability scale. International Journal of Human\u2013Computer Interaction 24 6 (2008) 574\u2013594.","DOI":"10.1080\/10447310802205776"},{"key":"e_1_3_3_2_6_2","unstructured":"Hansj\u00f6rg Bittner. 2012. Audio description guidelines: A comparison. New perspectives in translation 20 (2012) 41\u201361."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3451810"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Carmen Branje and Deborah Fels. 2012. LiveDescribe: Can Amateur Describers Create High-Quality Audio Description? Journal of Visual Impairment & Blindness 106 (03 2012) 154\u2013165.","DOI":"10.1177\/0145482X1210600304"},{"key":"e_1_3_3_2_9_2","first-page":"1","volume-title":"Proceedings of the ACM SIGCHI Conference on Human Factors in Computing Systems (CHI)","author":"Brashear Heather","year":"2021","unstructured":"Heather Brashear, Thad Starner, Paul Lukowicz, and Hermann Junker. 2021. Automated Video Description: Challenges and Opportunities. In Proceedings of the ACM SIGCHI Conference on Human Factors in Computing Systems (CHI). 1\u201314."},{"key":"e_1_3_3_2_10_2","unstructured":"John Brooke. 1996. SUS-A quick and dirty usability scale. Usability evaluation in industry 189 194 (1996) 4\u20137."},{"key":"e_1_3_3_2_11_2","volume-title":"PySceneDetect","author":"Castellano Brandon","unstructured":"Brandon Castellano. [n. d.]. PySceneDetect. https:\/\/github.com\/Breakthrough\/PySceneDetect"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676375"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545613"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715336.3735685"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Agnieszka Chmiel and Iwona Mazur. 2022. A homogenous or heterogeneous audience? Audio description preferences of persons with congenital blindness non-congenital blindness and low vision. Perspectives 30 3 (2022) 552\u2013567.","DOI":"10.1080\/0907676X.2021.1913198"},{"key":"e_1_3_3_2_16_2","volume-title":"Thematic Analysis: A Practical Guide","author":"Clarke Victoria","year":"2021","unstructured":"Victoria Clarke and Virginia Braun. 2021. Thematic Analysis: A Practical Guide. Sage Publications Ltd, Thousand Oaks, California, USA."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3675618"},{"key":"e_1_3_3_2_18_2","unstructured":"Described and Captioned Media Program (DCMP). 2024. Description Key for Educational Media. https:\/\/dcmp.org\/learn\/descriptionkey."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Anil\u00a0R Doshi and Oliver\u00a0P Hauser. 2024. Generative AI enhances individual creativity but reduces the collective diversity of novel content. Science Advances 10 28 (2024) eadn5290.","DOI":"10.1126\/sciadv.adn5290"},{"key":"e_1_3_3_2_20_2","unstructured":"Equal Entry. 2020. Audio Descriptions for 360 Degree Video: Best Practices. https:\/\/www.youtube.com\/watch?v=jOX6gxUZq8w&ab_channel=EqualEntry. YouTube video."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781003003052-24"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Nazaret Fresno Judit Castell\u00e0 and Olga Soler-Vilageliu. 2016. \u2018What should I say?\u2019Tentative criteria to prioritize information in the audio description of film characters. Researching audio description: New approaches (2016) 143\u2013167.","DOI":"10.1057\/978-1-137-56917-2_8"},{"key":"e_1_3_3_2_23_2","unstructured":"Nazaret Fresno Judit Castell\u00e0\u00a0Mate and Olga Soler\u00a0Vilageliu. 2014. Less is more. Effects of the amount of information and its presentation in the recall and reception of audio described characters. International Journal of Sciences: Basic and Applied Research (IJSBAR) (2014)."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781315707228"},{"key":"e_1_3_3_2_25_2","unstructured":"Yingqiang Gao Lukas Fischer Alexa Lintner and Sarah Ebling. 2024. Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.08860 (2024)."},{"key":"e_1_3_3_2_26_2","unstructured":"Aaron Hurst Adam Lerer Adam\u00a0P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et\u00a0al. 2024. Gpt-4o system card. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.21276 (2024)."},{"key":"e_1_3_3_2_27_2","unstructured":"Shasta Ihorn Yue-Ting Siu Aditya Bodi Lothar Narins Jose\u00a0M Castanon Yash Kant Abhishek Das Ilmi Yoon and Pooyan Fazli. 2021. NarrationBot and InfoBot: A Hybrid System for Automated Video Description. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2111.03994 (2021). https:\/\/arxiv.org\/abs\/2111.03994"},{"key":"e_1_3_3_2_28_2","volume-title":"Proceedings of the ACM SIGCHI Conference on Human Factors in Computing Systems (CHI)","author":"Jiang Lucy","year":"2024","unstructured":"Lucy Jiang, Crescentia Jung, Mahika Phutane, Abigale Stangl, and Shiri Azenkot. 2024. \"It\u2019s Kind of Context Dependent\": Understanding Blind and Low Vision People\u2019s Video Accessibility Preferences Across Viewing Scenarios. In Proceedings of the ACM SIGCHI Conference on Human Factors in Computing Systems (CHI)."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3517428.3550394"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597638.3608381"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Georgina Kleege and Scott Wallin. 2015. Audio description as a pedagogical tool. Disability Studies Quarterly 35 2 (2015).","DOI":"10.18061\/dsq.v35i2.4622"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01281"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714096"},{"key":"e_1_3_3_2_34_2","unstructured":"Wenkai Li Yichong Shen Nan Duan Ming Zhou Xu Sun and Wayne\u00a0Xin Zhao. 2023. BGE: Bridging the Gap between Text and Knowledge Graph for Knowledge-Based Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.12244 (2023)."},{"key":"e_1_3_3_2_35_2","unstructured":"K. Lucariello. 2024. DCMP includes AI scene description tool for students with visual disabilities. Retrieved from Perkins.org."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Iwona Mazur and Agnieszka Chmiel. 2021. Audio description training: A snapshot of the current practices. The Interpreter and Translator Trainer 15 1 (2021) 51\u201365.","DOI":"10.1080\/1750399X.2021.1880263"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Valerie\u00a0S Morash Yue-Ting Siu Joshua\u00a0A Miele Lucia Hasty and Steven Landau. 2015. Guiding novice web workers in making image descriptions using templates. ACM Transactions on Accessible Computing (TACCESS) 7 4 (2015) 1\u201321.","DOI":"10.1145\/2764916"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3675617"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373625.3418030"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3441852.3471201"},{"key":"e_1_3_3_2_41_2","first-page":"1","volume-title":"Proceedings of the International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS)","author":"Natalie Rosiana","year":"2021","unstructured":"Rosiana Natalie, Jolene Loh, Huei\u00a0Suen Tan, Joshua Tseng, Hernisa Kacorri, and Kotaro Hara. 2021. Uncovering patterns in reviewers\u2019 feedback to scene description authors. In Proceedings of the International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS). 1\u20134."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581023"},{"key":"e_1_3_3_2_43_2","unstructured":"Netflix Studios. 2024. Audio Description Style Guide v2.5. https:\/\/partnerhelp.netflixstudios.com\/hc\/en-us\/articles\/215510667-Audio-Description-Style-Guide-v2-5."},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642632"},{"key":"e_1_3_3_2_45_2","unstructured":"Ofcom. 2023. Ensuring the quality of TV and on-demand access services: Best practice guidelines. https:\/\/www.ofcom.org.uk\/__data\/assets\/pdf_file\/0026\/264291\/Ensuring-the-quality-of-TV-and-on-demand-access-services.pdf Accessed: April 15 2025."},{"key":"e_1_3_3_2_46_2","unstructured":"Ofcom. 2024. Provision of TV Access Services: Guidelines. https:\/\/www.ofcom.org.uk\/siteassets\/resources\/documents\/consultations\/category-2-6-weeks\/17danielpatt321@gmail.com8126-review-of-access-services-code\/associated-documents\/provision-of-tv-access-services-guidelines.pdf."},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"crossref","unstructured":"Jaclyn Packer Katie Vizenor and Joshua\u00a0A Miele. 2015. An overview of video description: history benefits and guidelines. Journal of Visual Impairment & Blindness 109 2 (2015) 83\u201393.","DOI":"10.1177\/0145482X1510900204"},{"key":"e_1_3_3_2_48_2","unstructured":"Emmanouela Patiniotaki. 2022. Audio Description for Dance Performances: An Artistic and Collaborative Approach. Status Quaestionis23 (2022)."},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415864"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-18374-9_32"},{"key":"e_1_3_3_2_51_2","unstructured":"Sonali Rai Joan Greening and Leen Petr\u00e9. 2010. A comparative study of audio description guidelines prevalent in different countries. Londra: Royal National Institute of Blind People (2010)."},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"crossref","unstructured":"Matthias\u00a0C Rillig Marlene \u00c5gerstrand Mohan Bi Kenneth\u00a0A Gould and Uli Sauerland. 2023. Risks and benefits of large language models for the environment. Environmental science & technology 57 9 (2023) 3464\u20133466.","DOI":"10.1021\/acs.est.3c01106"},{"key":"e_1_3_3_2_53_2","unstructured":"Rafael Rivera. 2024. LUAR-MUD: A Multilingual and Multi-Domain Large Language Model for Stylistic Representation. https:\/\/huggingface.co\/rrivera1849\/LUAR-MUD. Accessed: 2025-04-15."},{"key":"e_1_3_3_2_54_2","unstructured":"James Robert Marc Webbie et\u00a0al. 2018. Pydub. http:\/\/pydub.com\/"},{"key":"e_1_3_3_2_55_2","unstructured":"Keita Saito Akifumi Wachi Koki Wataoka and Youhei Akimoto. 2023. Verbosity bias in preference labeling by large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.10076 (2023)."},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"crossref","unstructured":"Eva Schaeffer-Lacroix Nina Reviers and Elena Di\u00a0Giovanni. 2023. Beyond objectivity in audio description: New practices and perspectives. Journal of Audiovisual Translation 6 2 (2023) 1\u20137.","DOI":"10.47476\/jat.v6i2.2023.309"},{"key":"e_1_3_3_2_57_2","unstructured":"Silero Team. 2024. Silero VAD: pre-trained enterprise-grade Voice Activity Detector (VAD) Number Detector and Language Classifier. https:\/\/github.com\/snakers4\/silero-vad."},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"crossref","unstructured":"Hannah Thompson. 2018. Audio description: Turning access to film into cinema art. Disability Studies Quarterly 38 3 (2018).","DOI":"10.18061\/dsq.v38i3.6487"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642839"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"crossref","unstructured":"A. Walczak and L. Fryer. 2017. Creative description: The impact of audio description style on presence in visually impaired audiences. British Journal of Visual Impairment 35 1 (2017) 6\u201317.","DOI":"10.1177\/0264619616661603"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445347"},{"key":"e_1_3_3_2_62_2","unstructured":"World Wide Web Consortium (W3C). 2008. Understanding Success Criterion 1.2.3: Audio Description or Media Alternative (Prerecorded). https:\/\/www.w3.org\/TR\/UNDERSTANDING-WCAG20\/media-equiv-audio-desc-only.html."},{"key":"e_1_3_3_2_63_2","unstructured":"YouDescribe. [n. d.]. https:\/\/youdescribe.org\/."},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357236.3395433"}],"event":{"name":"ASSETS '25: The 27th International ACM SIGACCESS Conference on Computers and Accessibility","location":"Denver Colorado USA","acronym":"ASSETS '25","sponsor":["SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3663547.3746320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T17:58:46Z","timestamp":1767981526000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3663547.3746320"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":63,"alternative-id":["10.1145\/3663547.3746320","10.1145\/3663547"],"URL":"https:\/\/doi.org\/10.1145\/3663547.3746320","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]},"assertion":[{"value":"2025-10-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}