I knew Google Voice would have multiple uses for people who are deaf and hearing impaired, but I didn’t expect this news to come so fast: Google is adding automatic captions to YouTube videos. Google announced the news today on its official Google blog, and while the feature is definitely a work-in-progress, it’s an exciting start to machine-generated video captions.
Many people know that Google created a YouTube caption system about a year ago. It required users to upload captions themselves, a time-consuming process, which meant that most videos did not get captioned and were inaccessible to people with hearing impairments.
With the new “auto-caps”, Google is combining its automatic speech recognition (ASR) technology with the YouTube caption system. Auto-caps use the same voice recognition algorithms in Google Voice to automatically generate captions for video. “The captions will not always be perfect, but even when they’re off, they can still be helpful,” writes Ken Harrenstien, a Google software engineer who is deaf, in Google’s Blog. “And the technology will continue to improve with time,” he adds.
Google is also launching automatic caption timing, or “auto-timing,” to make it significantly easier to create captions manually. With auto-timing, you can create a simple text file with all the words in the video and Google will use its ASR technology to figure out when the words are spoken and create perfectly timed captions that are synced with your video. Google hopes these two new features will “significantly lower the barriers for video owners who want to add captions, but who don’t have the time or resources to create professional caption tracks,” writes Harrenstien.
Auto caps also benefits people who do not have disabilities. It enables people around the world to access video content in any of 51 languages. Captions can also improve search and even enable users to jump to the exact parts of the videos they’re looking for.
For the initial launch, auto-caps are only visible on a handful of partner channels: UC Berkeley, Stanford, MIT, Yale, UCLA, Duke, UCTV, Columbia, PBS, National Geographic, Demand Media, UNSW and most Google and YouTube channels. Google wants to get feedback from both viewers and video owners before they roll them out more broadly. Auto-timing will roll out globally for all English-language videos on YouTube.
Meanwhile, the Federal Communications Commission is hearing from disability advocates to find ways to make broadband — including web T.V. and video programming — accessible to people who are deaf and blind.
Thanks, Google, for taking a giant step towards video accessibility for all.