Researchers Revolutionize Closed Captioning
From: PhysOrg.com - 03/22/2012
By: Lisa Zyga 

Hefei University of Technology researchers led by Meng Wang have developed a
closed-captioning technique in which the text appears in translucent talk
bubbles next to the speaker. The researchers say their approach offers
several advantages over existing static-captioning technology for improving
the viewing experience for hearing-impaired people. Their technique is known
as dynamic captioning because the text appears in different locations and
styles to better reflect the speaker's identity and vocal dynamics. The
researchers developed algorithms to automatically identify the speaker using
the video's script file and lip motion detection technology. The technology
uses visual saliency analysis to automatically find the optimal position for
the talk bubble so there is as little interference as possible with the
visual scene. During testing, 60 hearing-impaired people viewed films using
the new technology. The study found that 53 of the testers preferred dynamic
captioning over static captioning. “The whole technique was motivated by
solving the difficulties of hearing-impaired viewers in watching videos,”
Wang says. “These viewers have difficulty in recognizing who is speaking, so
we put scripts around the speaker's face; they have difficulty in tracking
scripts, so we synchronously highlight the scripts.”  

Read the entire article at:
http://www.physorg.com/news/2012-03-revolutionize-captioning.html

Link:
Meng Wang
https://sites.google.com/site/mengwangsite/