[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-572443-105":53,"doc-detail-572443-en":126},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":119,"head_meta":121,"extra_data":123,"updated_unix":125},105,"en","adcanvas-accessible-and-conversational-audio-description-authoring-for-blind-and-low-vision-creators","ADCanvas - Accessible and Conversational Audio Description Authoring for Blind and Low Vision Creators","","Audio Description (AD) provides essential access to visual media for blind and low vision (BLV) audiences. Yet current AD production tools remain largely inaccessible to BLV creators, who have expertise but face barriers from visually driven interfaces. ADCanvas is presented as a multimodal authoring system enabling non-visual control for end-to-end AD creation, visual question answering, script generation, and modification.",{"@graph":63,"@context":118},[64,80,101],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":11,"@type":70,"position":76},"https://docshare.wps.com/template/presentations/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/adcanvas-accessible-and-conversational-audio-description-authoring-for-blind-and-low-vision-creators/572443/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/adcanvas-accessible-and-conversational-audio-description-authoring-for-blind-and-low-vision-creators/572443.png","ImageObject",442,249,{"name":88,"@type":89},"jay","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-10-19","2026-10-13",true,{"@type":98,"interactionType":99,"userInteractionCount":79},"InteractionCounter",{"@type":100},"ViewAction",{"@type":102,"mainEntity":103},"FAQPage",[104,110,114],{"name":105,"@type":106,"acceptedAnswer":107},"What problem does ADCanvas address for blind and low vision creators?","Question",{"text":108,"@type":109},"It targets the inaccessibility of existing audio description (AD) authoring tools, which rely on visual interfaces and hinder BLV creators’ ability to create AD independently.","Answer",{"name":111,"@type":106,"acceptedAnswer":112},"How does ADCanvas support non-visual AD authoring?",{"text":113,"@type":109},"ADCanvas combines conversational interaction with keyboard-based playback controls and a plain-text, screen reader–accessible editor for editing AD scripts.",{"name":115,"@type":106,"acceptedAnswer":116},"What did the study with 12 BLV video creators find?",{"text":117,"@type":109},"Participants used the conversational agent as an informational and drafting aide while retaining agency through verification and editing, viewing themselves as curators filtering model-provided information for their audiences.","https://schema.org",{"og:url":78,"og:type":120,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":122,"canonical":78},"index,follow",{"doc_id":124,"site_id":56},572443,1792316589,{"code":4,"msg":5,"data":127},{"doc_id":124,"user_id":128,"nickname":88,"user_avatar":129,"doc_module":9,"category_id":8,"category_name":11,"doc_title":59,"doc_description":61,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":79,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":45,"language":135,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":136,"faqs":137,"seo_title":138,"seo_description":61,"update_tm":139,"read_time":140},3985747858866,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","ADCanvas: Accessible and Conversational Audio Description Authoring for Blind and Low Vision Creators  \nFranklin Mingzhe Li  \nHuman-Computer Interaction Institute Carnegie Mellon University Pittsburgh, Pennsylvania, USA Google New York, New York, USA [mingzhe2@cs.cmu.edu](mingzhe2@cs.cmu.edu)  \nMichael Xieyang Liu  \nGoogle DeepMind Pittsburgh, Pennsylvania, USA[lxieyang@google.com](lxieyang@google.com)  \nCynthia L Bennett∗  \nGoogle  \nNew York, New York, USA [clbennett@google.com](clbennett@google.com)  \nShaun K. Kane∗  \nGoogle Research Boulder, Colorado, USA [shaunkane@google.com](shaunkane@google.com)  \nd  \na  \nd2  \n d3   Ctrl + O   \nd1  \nFigure 1: ADCanvas allows the user to control the video (a) through both screen reader compatible buttons (a) and hotkeys (b). The user can communicate with the conversational agent through the textbox (c1) to ask questions or manipulate the AD script (c, d). The user can also edit the AD script through the WebVTT-based AD editor (d, d2) line by line (d1) with a screen reader (e). Upon completing the AD scripts, the user can play the AD narration with the original soundtrack by using hotkey (d3).  \n∗ These authors jointly supervised this work.  \nThis work is licensed under a Creative Commons Attribution 4.0 International License. CHI’26, Barcelona, Spain  \nAbstract  \nAudio Description (AD) provides essential access to visual media for blind and low vision (BLV) audiences. Yet current AD production tools remain largely inaccessible to BLV video creators, who possess  \n© 2026 Copyright held by the owner/author(s) . ACM ISBN 979-8-4007-2278-3/26/04  \n[https://doi.org/10.1145/3772318.3791158](https://doi.org/10.1145/3772318.3791158)  \nvaluable expertise but face barriers due to visually-driven interfaces. We present ADCanvas, a multimodal authoring system that supports non-visual control over audio description (AD) creation. ADCanvas combines conversational interaction with keyboardbased playback control and a plain-text, screen reader–accessible editor to support end-to-end AD authoring and visual question answering (VQA). Combining screen-reader-friendly controls with a multimodal LLM agent, ADCanvas supports live VQA, script generation, and AD modification. Through a user study with 12 BLV video creators, we find that users adopt the conversational agent as an informational aide and drafting assistant, while maintaining agency through verification and editing. For example, participants saw themselves as curators who received information from the model and filtered it down for their audience. Our findings offer design implications for accessible media tools, including precise editing controls, accessibility support for creative ideation, and configurable rules for human-AI collaboration.  \nCCS Concepts  \n• Human-centered computing → Accessibility systems and tools.  \nKeywords  \nAccessibility, Audio Description, Conversational Agent, MLLM, Blind, Low Vision, AD Creator  \nACM Reference Format:  \nFranklin Mingzhe Li, Michael Xieyang Liu, Cynthia L Bennett, and Shaun K. Kane. 2026. ADCanvas: Accessible and Conversational Audio Description Authoring for Blind and Low Vision Creators. In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI’26), April 13–17, 2026, Barcelona, Spain. ACM, New York, NY, USA, 21 pages. [https:](https:)//[doi.org/10.1145/3772318.3791158](doi.org/10.1145/3772318.3791158)  \n1 Introduction  \nAudio Description (AD) is a critical access modality that augments visual media content with spoken narration for people who are blind or have low vision (BLV) [15, 35, 59, 72] . Far beyond an auxiliary feature, AD is a primary means through which BLV audiences access film, television, and user-generated videos posted on social media [29, 34] . Narration is inserted into gaps with no dialogue or important sounds, and might describe a character’s critical facial expression, the intricate details of a fantasy setting, or the key actions in a fast-paced sequence","cbCaia0O0UawwkYg","https://ap.wps.com/l/cbCaia0O0UawwkYg","pdf",1740385,"English","# Abstract\n# Keywords\n# 1 Introduction","[{\"question\":\"What problem does ADCanvas address for blind and low vision creators?\",\"answer\":\"It targets the inaccessibility of existing audio description (AD) authoring tools, which rely on visual interfaces and hinder BLV creators’ ability to create AD independently.\"},{\"question\":\"How does ADCanvas support non-visual AD authoring?\",\"answer\":\"ADCanvas combines conversational interaction with keyboard-based playback controls and a plain-text, screen reader–accessible editor for editing AD scripts.\"},{\"question\":\"What did the study with 12 BLV video creators find?\",\"answer\":\"Participants used the conversational agent as an informational and drafting aide while retaining agency through verification and editing, viewing themselves as curators filtering model-provided information for their audiences.\"}]","ADCanvas - Accessible and Conversational Audio Description Authoring for Blind and Low Vision Creators | PDF",1791927421,7]