Related Experiment Videos
"Better Than Nothing" or Not Enough? User-Centered Reflections on AI-Generated Audio Descriptions Across Media
Diana Yee1, Amina Kobenova2, Rohan Jhangiani3
1Computational Media University of California, Santa Cruz Santa Cruz, California, USA.
None:
AI-generated audio descriptions (ADs) offer scalable solutions for making visual media accessible to blind and low-vision (BLV) audiences. Nevertheless, little is known about how BLV users experience and evaluate these descriptions across emerging platforms. In this qualitative study, we conducted semi-structured interviews with ten (N=10) BLV participants, recruited based on divergences in prior survey ratings, to explore their perceptions of both human- and AI-generated ADs in contexts ranging from traditional film to short-form video and livestreams. Thematic analysis revealed five key themes: (1) information prioritization and genre-sensitive details, (2) the "better-than-nothing" consensus tempered by emotional and contextual gaps in AI-generated ADs, (3) the social dynamics of shared viewing, (4) accessibility deserts on new media platforms, and (5) the artistry-precision dilemma. Our findings highlight the need for adaptive, transparent, and user-informed AD systems that balance narrative resonance with efficiency. We conclude with design recommendations for co-designing AI-assisted accessibility tools in partnership with BLV communities.
Related Concept Videos
Sound Intensity Level
The human ear can perceive an extensive range of sound intensity, necessitating the use of the logarithmic scale to define a physical quantity—the intensity level. It is a ratio of two intensities and hence a...
Non-equilibrium in the Cell
Auditory Pathway
When viewed cross-sectionally, the cochlea reveals the scala vestibuli and scala tympani flanking the...
Impression Management Techniques IV: Altercasting
Sound Intensity
Hearing