Google, the owner of video exchange website YouTube, has started providing automatic captions for some English language videos on the website, increasing accessibility for deaf users.
The ‘auto-caps’ system is made possible by Google’s own automatic speech recognition (ASR) technology, working alongside the current YouTube captioning system.
Although captions are already available on YouTube, it was previously necessary for the owner of the video to insert them manually – a time-consuming task, given the sheer number of videos uploaded to the site.
Ken Harrenstien, a Google software engineer who is also deaf, said recently on the official Google Blog: “Every minute, 20 hours of video are uploaded. 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.”
Google’s ASR technology is also being used to make the manual captioning system on YouTube easier and more efficient to use. ‘Auto-timing’ will allow users to caption a video without any specialist technical knowledge through creation of a simple text file with a transcript of the video’s speech. The ASR then converts this text to captions by searching for the words at the relevant point in the video.
The Royal National Institute for Deaf People (RNID: www.rnid.org.uk ) have supported Google’s decision, saying that all on-demand content should be accessible. RNID director of external affairs, Emma Harrison, told E-Access Bulletin: “RNID welcomes Google taking this first step towards making YouTube more accessible for deaf viewers.”
Auto-caps are currently live on a series of educational YouTube channels (including National Geographic and some American universities), in order for Google to gather feedback before rolling out the system on a broader basis. The auto-timing feature is currently available on all English-language YouTube videos.