San Francisco — Google owned popular video-sharing site YouTube, on Thursday in a remarkable development announced that it is unveiling its auto-caption feature for millions of deaf and hard of hearing Internet users, to all English-language videos on the video-sharing website.
YouTube said this use of speech recognition technology is probably the biggest experiment of its kind online, a move that will not only benefit deaf users, but also people who watch videos in extremely noisy places, like airport terminals.
Previously, YouTube were manually able to add captions to a small amount of videos since 2008 and in November of last year the site started out offering machine-generated captions for about a dozen partner channels.
Hiroto Tokusei, a YouTube product manager, said in a blog post on Thursday that the automatic caption, or auto-caption, feature was now being expanded to all videos on the site in English.
Auto-captioning uses speech-to-text technology to generate subtitles.
“Making video easily accessible is something we are working hard to address at YouTube,” said Tokusei, citing studies that predict that over 700 million people worldwide will suffer from hearing impairment by 2015.
“A core part of YouTube’s DNA is access to content,” said the company’s product manager.
Most, if not all, YouTube videos now include a “CC” button that, if clicked, will automatically activate the closed-captioning technology. The technology processes the audio feed, using the speech-recognition technology used in the core voice search feature that has also built into the Android voice search feature, the GOOG-411 phone search, and other products.
For now, YouTube can only “perceive” spoken English in order to auto-generate the caption track. However, Google’s translation services can also take the English machine-transcription track and translate it to up to fifty languages. Adding more languages that Google understands “is a priority,” said Mike Cohen, a speech technologist at Google.
“This is huge,” said Ken Harrenstien, a software engineer at Google and one of the project’s leaders. “You can go to any video online and now you can see some captions. It is not perfect; we know it is not perfect. Sometimes it is funny. But I love it.”
Google’s YouTube Captions, Translation:
An example of Google’s machine translation and closed captioning. It is not perfect.
Around twenty hours of videos are uploaded to YouTube every minute; Google could not provide a timetable on when all of the videos would be captioned, but it will be “very soon,” executives said.
The auto-captioning feature will make YouTube videos “more accessible to people who have hearing disabilities or who speak different languages,” the YouTube project manager said.
Google has also made alliance with a number of content partners, including UC Berkeley, Stanford, Duke University, MIT, PBS, National Geographics, and Demand Media.