YouTube launches auto-caption feature for deaf viewers

by Stevie Smith - Nov 20 2009, 12:45

Last week, online video-sharing service YouTube extended its usage appeal with the formal unveiling of 720p and 1080p high-definition clip support. This week, the Google-owned Web site is enhancing its level of accessibility by introducing a machine-generated automatic caption feature for deaf viewers.

Rolled out by Google software engineer Ken Harrenstien, who has played a pivotal role in developing the new feature (and also happens to be deaf), Google’s automatic speech recognition (ASR) technology has been combined with YouTube’s existing caption system in order to provide active uploaders and visiting viewers with the benefit of “auto-caps”.

“Every minute, 20 hours of video are uploaded [to YouTube],” outlined Harrenstien in a Google blog post. “How can we expect every video owner to spend the time and effort necessary to add captions to their videos? Even with all of the captioning support already available on YouTube, the majority of user-generated video content online is still inaccessible to people like me.”

To address this time-consuming process on a site that receives in excess of one billion hits every day, Google’s auto-caps feature utilises the same voice recognition algorithms in Google Voice to automatically generate captions for uploaded videos.

“The captions will not always be perfect,” explained Harrenstien, “but even when they’re off, they can still be helpful – and the technology will continue to improve with time.”

Announced alongside auto-caps, Google is also launching an auto-timing tool that makes manual caption creation considerably easier as users need only create a simple text file with all the words in the video and Google will then apply its ASR technology to convert that text into on-screen captions that accompany the footage.

While both features will debut today (in English), auto-caps usage will initially be restricted to partner channels such as National Geographic, PBS, Stanford, UC Berkeley, MIT, Yale, UCLA, and Demand Media, whilst Google and YouTube work to process feedback, iron out any issues, and increase the service’s accuracy and reliability.

Around the Web