Speaker-following Video Subtitles
This addresses the issue of disrupted viewing and eyestrain for video viewers, representing an incremental improvement over existing subtitle methods.
The paper tackles the problem of subtitle placement in video by proposing a method that positions subtitles next to speakers, using audio-visual detection and global optimization, with a usability study showing it outperforms conventional and dynamic methods in enhancing viewing experience and reducing eyestrain.
We propose a new method for improving the presentation of subtitles in video (e.g. TV and movies). With conventional subtitles, the viewer has to constantly look away from the main viewing area to read the subtitles at the bottom of the screen, which disrupts the viewing experience and causes unnecessary eyestrain. Our method places on-screen subtitles next to the respective speakers to allow the viewer to follow the visual content while simultaneously reading the subtitles. We use novel identification algorithms to detect the speakers based on audio and visual information. Then the placement of the subtitles is determined using global optimization. A comprehensive usability study indicated that our subtitle placement method outperformed both conventional fixed-position subtitling and another previous dynamic subtitling method in terms of enhancing the overall viewing experience and reducing eyestrain.