YouTube Rolls Out Auto-Captioning


TechCrunch reports that YouTube has launched auto-captions for English-language videos. In short, they're using machine translation to provide subtitles (also known as "closed captioning") on many of their videos. Not every video can be auto-captioned, and the captions won't be perfect -- in fact, in many cases, I expect the captions will be quite bad. But it's a big step, and an exciting start. Video publishers can fine-tune the captions themselves, which should lead to a huge increase the amount (and quality) of closed-captioned content available online.

Here are some clarifications from Google's engineering team about the auto-captions and their limitations:

• While we plan to broaden the feature to include more languages in the months to come, currently, auto-captioning is only for videos where English is spoken. • Just like any speech recognition application, auto-captions require a clearly spoken audio track. Videos with background noise or a muffled voice can't be auto-captioned. President Obama's speech on the recent Chilean Earthquake is a good example of the kind of audio that works for auto-captions. • Auto-captions aren't perfect and just like any other transcription, the owner of the video needs to check to make sure they're accurate. In other cases, the audio file may not be good enough to generate auto-captions. But please be patient -- our speech recognition technology gets better every day. • Auto-captions should be available to everyone who's interested in using them. We're also working to provide auto-captions for all past user uploads that fit the above mentioned requirements. If you're having trouble enabling them for your video, please visit our Help Center: this article is for uploaders and this article is for viewers.

Here's a video by students at the California School for the Deaf in Fremont, using the auto-captioning feature, explaining how the feature helps the deaf -- and those who are learning English:

After the jump, check out a regular video and note how the captions aren't always perfect. But...better than nothing.

Here's John Green, former _floss writer and blogger. You may need to hit the little "CC" button to turn on captions, depending on your platform. Also, if you're using the HTML5 beta (in other words, if you're an extreme nerd like me), captions don't work -- until you opt out of the beta. Now, I'll be honest -- the auto-captioning kinda sucks here. Then again, it's a whole lot better than nothing, and Green is using a bunch of self-coined terms like "Nerdfighter" and "Nerdfighteria."

I'm wondering if anyone can find a good example of the auto-captioning working well? Post links in the comments. (Note that Google mentions Obama's recent speech on the Chilean earthquake as an example of the captions working well. It looks to me like those captions have been hand-tweaked, as another copy of that same speech here shows lots of mistakes. Not awful mistakes, but certainly not perfect.)