In a step to make YouTube videos more accessible to deaf people, as well as to anyone else searching for videos online, Google has launched an automatic video captioning service.
Captioned videos are not entirely new at YouTube. Google first introduced manual user-generated video captioning three years ago, and people have already used the existing service to caption hundreds of thousands of videos.
But the new auto captioning service will exploit the speech-recognition algorithms used in
Google Voice to produce captions automatically.
Ken Harrenstien, the software engineer who created the new “auto-cap” technology, acknowledges that the captions will not always be perfect right now.
But Harrenstien, who is deaf, also predicts that the new technology will continue to improve over time. “The majority of user-generated video content online is still inaccessible to people like me,” he wrote in a
Initially, the machine-generated captions will be generated in English only, and they will only be visible on 13 partner channels, But Harrenstien suggests that, with machine translation, the captions will ultimately allow 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,” according to Harrenstien.
Beyond the auto-captioning, Google also launched a new service called automatic caption timing, or auto-timing, aimed at easing the process of creating captions manually.
“With auto-timing, you no longer need to have special expertise to create your own captions in YouTube. All you need to do is create a simple text file with all the words in the video and we’ll use Google’s ASR technology to figure out when the words are spoken and create captions for your video,” he explains.