Rescribe

Abstract

Audio descriptions make videos accessible to those who cannot see them by describing visual content in audio. Producing audio descriptions is challenging due to the synchronous nature of the audio description that must fit into gaps of other video content. An experienced audio description author will produce content that fits narration necessary to understand, enjoy, or experience the video content into the time available. This can be especially tricky for novices to do well. In this paper, we introduce a tool, Rescribe, that helps authors create and refine their audio descriptions. Using Rescribe, authors first create a draft of all the content they would like to include in the audio description. Rescribe then uses a dynamic programming approach to optimize between the length of the audio description, available automatic shortening approaches, and source track lengthening approaches. Authors can iteratively visualize and refine the audio descriptions produced by Rescribe, working in concert with the tool. We evaluate the effectiveness of Rescribe through interviews with blind and visually impaired audio description users who give feedback on Rescribe results. In addition, we invite novice users to create audio descriptions with Rescribe and another tool, finding that users produce audio descriptions with fewer placement errors using Rescribe.

AVscript: Accessible Video Editing with Audio-Visual Scripts

“…To address this challenge, AVscript provides access to visual content including: a summary of key visual moments via scene descriptions, a list of low-level objects via inspect mode, and ondemand access to visuals of interest via search. While creators using AVscript occasionally listened to the video and scene descriptions linearly (similar to how BLV audiences currently listen to audio descriptions that describe visual content in a video alongside the video narration [40,57]), creators also used scene descriptions for new use cases including skimming the outline of scene descriptions to gain an overview of visual content, and clicking on scene descriptions to navigate to video scenes (similar to how sighted video creators use video keyframes to navigate with timeline-based video editing tools [4,6]). Scene description-based navigation helped address an existing challenge for video creators (C4.…”

“…Videos are inaccessible to BLV audiences when the visual content in the video is not described by the audio (e.g., travel videos with scenic shots set to music) [45,46,60]. To make videos accessible, video creators [57], volunteers [31], or professional audio describers [1] add audio descriptions to describe important visual content that is not understandable from the audio alone. As authoring audio descriptions is challenging, prior work developed tools that help creators gain feedback on audio descriptions [49,69], respond to audience requests for descriptions [31], optimize descriptions to fit within time available [57], and recognize mismatches between audio and visuals to add descriptions as they capture [60] or edit [46] videos.…”

“…To make videos accessible, video creators [57], volunteers [31], or professional audio describers [1] add audio descriptions to describe important visual content that is not understandable from the audio alone. As authoring audio descriptions is challenging, prior work developed tools that help creators gain feedback on audio descriptions [49,69], respond to audience requests for descriptions [31], optimize descriptions to fit within time available [57], and recognize mismatches between audio and visuals to add descriptions as they capture [60] or edit [46] videos. Beyond helping creators author accessible videos, prior work makes inaccessible videos accessible on demand by generating automatic [83] or interactive [29,59] visual descriptions.…”

“…Just as visual inspection presents an accessibility barrier for BLV creators authoring static visuals (e.g., photos [8], presentations [61], documents [15]), relying on visual inspection makes video editing inaccessible to a growing number of blind and low vision (BLV) video creators [71] who author and share general-purpose and accessibility-focused videos including vlogs, reviews, and tutorials online. While prior work explored how to make videos accessible to BLV audience members [45,46,57], and how to make video editing more efficient for sighted creators [9,14,28], existing work has not yet explored how to make video editing accessible to BLV creators.…”

Exploring Community-Driven Descriptions for Making Livestreams Accessible

“…audio descriptions. Prior work explored how to create audio descriptions for recorded videos such as films [3,36,46], user-generated videos [19, 28,29,37,50], slide presentations [38,39] and GIFs [11] by providing computational description support [29,37,38,50,54] and proposing what to describe for specific video types (e.g., GIFs [11], films [46]). Previous work has not yet explored technology to support live descriptions or description preferences for livestream-specific content (e.g., long expert streams).…”