Google Begins Implementing Auto-Captioning on YouTube

And just like that, it renders my arguments about the company being evil completely moot. Because, as it turns out, I have a deaf son with cochlear implants. And he's been looking forward to this change for months, and is excited by what this means for his ability to access video content online. And while it's easy--maybe too easy--to make jokes about the Google Voice-based transcription technology that's making this work, let's be serious here for a moment. This is a milestone in technology accessibility. And when a company as big as Google does something like this on a site as popular as YouTube, we all benefit. So as a tiny pseudo-representative of the Deaf Community, Google, I thank you for this. The happy look in my son's eyes is enough to know that you've already made a difference.

Here's one news link describing the update.

And here's some info from Google, from back in November, when they announced they were doing this.

We've combined Google's automatic speech recognition (ASR) technology with the YouTube caption system to offer automatic captions, or auto-caps for short. Auto-caps use the same voice recognition algorithms in Google Voice to automatically generate captions for video. The captions will not always be perfect (check out the video below for an amusing example), but even when they're off, they can still be helpful—and the technology will continue to improve with time.

In addition to automatic captions, we’re also launching automatic caption timing, or auto-timing, to make it significantly easier to create 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. This should 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.

Click here to watch a YouTube video describing this important service.

Right now, captioning doesn't appear to be broadly available, but I've already seen some nice examples of it in action. Obviously, the better the audio in the clip, the better the auto-captioning. But the company is really going the extra mile by allowing people to manually edit the caption tracks. It's just a nice thing they're doing here, it really is.

Discuss this Article 27

Logjamming
on Mar 6, 2010
www.engadget.com/.../microsofts-courier-digital-journal-exclusive-pictur... Hey Paul, talk about render: how about another 'Look-Microsoft-released-rendered-mockups-and-some-pictures-about-another-product-that-will-not-be-released-anytime-soon-but-will-keep-Microsoftapologists-believing-Microsoft-is-about-innovation'? This is absolutely laughable! Apple has an iPad coming out in four weeks and what does Microsoft do to keep it apologists happy? Mockups and concepts. Even a hardly working WinMobile 7 demo needs 11 months after announcement before it can be released. This mockup will bring Microsoft-apologists in the iPad-age somewhere mid 2013. Just about the same amount of time Windows is lagging behind OSX.
Arfgo
on Mar 6, 2010
Why do you keep complaining Paul always talks about Apple if you will attempt to talk about it in every posts? Back on topic: this is actually pretty impressive. I have a friend with hearing problems and he will be thrilled.
gfryesc1
on Mar 6, 2010
'we all benefit'? Why is it that everything paul uses personally is interesting to 'us all' but anything that doesn't relate to his personal interests is uninteresting or has 'lost' and people 'need to get over it'? and people that do still use it are 'lemmings'... wherever would we be without his sage-like technological advice. Sorry for your deaf son and all though you shouldn't be using him in this way. For the vast majority of us it really doesn't alter the 'google is evil/isn't evil' rating in the slightest.
Webdev511
on Mar 6, 2010
Doing this on YouTube is no small feat. I think that only leaves the Zune Marketplace that doesn't support or hasn't announced support for captioning. @Logjamming. 1. Sorry, but iPodTouch XL isn't innovation, it's about making a really big iPodTouch. IMHO, the iPhone is the last truely innovative product Apple has released and that was three years ago.
Waethorn
on Mar 6, 2010
"Sorry for your deaf son and all though you shouldn't be using him in this way." I'd be more sorry for him that Google is now tagging him as having a physical condition and then selling his personal info to advertisers to target him with hearing aid ads.
DRWAM
on Mar 6, 2010
This is like saying that the devil did something good by offering Eve some food.
Logjamming
on Mar 6, 2010
@ Webdev511 said: At least the iPad will be out in four weeks. Which is three years after the iPhone, but still 8 months ahead of WinMobile 7 (which is not even on par with iPhone OS 2.0). But I'm sure you'd rather have a rendered flying car that can take off from your lawn and uses no petrol than a real-life Mercedes V12. The Courier is not real. It's a Microsoft bait. But anyone can design such a rendered mockup. Getting it to work properly with hardware and software whilst also making a useable UI that doesn't drain a battery in 30 minutes is a whole different ballgame. And while Microsoft is busy developing vaporware, the iPad is being loaded onto containers making its way to customers. Most people, however, aren't fooled by
mikegalos@msn.com
on Mar 6, 2010
Waethorn, "I'd be more sorry for him that Google is now tagging him as having a physical condition and then selling his personal info to advertisers to target him with hearing aid ads." That really wouldn't be that profitable for them. Identifying hearing impaired users is both a relatively small market and one that's already relatively easy to target. What it actually does is allow Google to use those auto-generated text transcripts of the videos as a source of keyword tags that Google can attach to the profiles of everyone who watches each video.
robertsjoe
on Mar 6, 2010
Google is not evil. Neither is Apple, for that matter. Only Microsoft is Evil. They have been known as evil, and still are today. Nothing's changed.
Dr. Daniel Jackson
on Mar 6, 2010
"Only Microsoft is Evil" Yes, Steve Ballmer is a Goa'uld, I believe that the Trust has taken over Microsoft and had planed to use captioning on you tube videos to enslave the human race, but too bad Google beat them to it.
redunion1940
on Mar 6, 2010
Corporations can't be evil, they can be unethical, but in all reality a Corporation is a fictitious person, who relies on the people inside it to not be unethical. As far as we know I'm pretty sure Microsoft doesn't employ child labor, takes random people and kill them, because they don't like them, through there policies force people to commit suicide if they lose a prototype. So forth and so forth. Microsoft has done some aggressive things like, at one point not allow OEM's to install crapware on computers sold with Windows, provide the world with a free web browser when web browser cost money to use(evil) Buy small companies and use there products or ideas in later releases for the general public(evil). In all honestly they did try to use there monopoly to gain more power, but point to me one person who has never done this, use an advantage from one area to gain an advantage in another. As for Google people should watch them to make sure they remain ethical with all that personal information they gather, and not use there monopoly to gain an advantage in other areas like OS, Smart Phone, or the Cloud.
redunion1940
on Mar 6, 2010
Corporations can't be evil, they can be unethical, but in all reality a Corporation is a fictitious person, who relies on the people inside it to not be unethical. As far as we know I'm pretty sure Microsoft doesn't employ child labor, takes random people and kill them, because they don't like them, through there policies force people to commit suicide if they lose a prototype. So forth and so forth. Microsoft has done some aggressive things like, at one point not allow OEM's to install crapware on computers sold with Windows, provide the world with a free web browser when web browser cost money to use(evil) Buy small companies and use there products or ideas in later releases for the general public(evil). In all honestly they did try to use there monopoly to gain more power, but point to me one person who has never done this, use an advantage from one area to gain an advantage in another. As for Google people should watch them to make sure they remain ethical with all that personal information they gather, and not use there monopoly to gain an advantage in other areas like OS, Smart Phone, or the Cloud.
redunion1940
on Mar 6, 2010
ah the evil double post interesting.
Arfgo
on Mar 6, 2010
They have been saying homosexuals are evil for a while now. You are such a fool... While one corporation is trying to ruin you it's all kittens and sunshine for the other corporation. This is like a really bad commercial...
Backup77
on Mar 6, 2010
If this helps hearing impaired people lead a normal life why not, in my opinion there should be more of it. Does everyone have to look at the negative side of it.
DRWAM
on Mar 6, 2010
@ Backup Actually, I'm just making a joke. Some of you have some real issues. MAC vs Apple crap, name calling...wow! Some of MS fanboys do exactly what you are complaining about Mac fanboys doing. It's strange that they just don't see it, and allow the Mac fanboys to achieve their goal, which is getting on their nerves. Too bad there's not an app for that!. But even if there was a self improvement app, some ppl on this site are such Apple haters, that they would not use it to even save their own life.
Waethorn
on Mar 6, 2010
"At least the iPad will be out in four weeks. Which is three years after the iPhone, but still 8 months ahead of WinMobile 7 (which is not even on par with iPhone OS 2.0)." Ya, because cut-and-paste and multitasking are SOOO hard to implement in modern OS's. But WAIT! Windows Mobile has had both since it's inception, even before it was known as "Windows Mobile". I guess iPhone must have both since "Windows Mobile is playing catch-up". So how is that going for ya? Answer: 3 years later, and the iPhone is only 50% there. "Most people, however, aren't fooled by...." you, logjam.
Waethorn
on Mar 6, 2010
BTW: Looking at the capabilities of my existing phone (WM 6.1 HTC Touch Diamond [1]), and comparing to Windows Phone 7, I can see functionality that hasn't been shown in the new software. One is an RSS feed/OTA-podcast reader. The other is a Remote Desktop client. My contract is coming due around the same time as these come out, so I'll keep an eye out for those features to show up. The Remote Desktop stuff isn't a huge deal, but an RSS reader is a necessity. Windows Live Messenger would also be a big plus, and I haven't even seen that yet. I think I'll wait until there's a hardware keyboard form factor too though. Er....back to Google... um.... Ok ya: "What it actually does is allow Google to use those auto-generated text transcripts of the videos as a source of keyword tags that Google can attach to the profiles of everyone who watches each video." I'm kind of surprised Google isn't doing video ads yet. Certainly, they could just fingerprint audio bites and musical cues to relate video content to other related videos and to video ads. Of course, they could just as easily do the same with the images.
DRWAM
on Mar 6, 2010
I'm gonna prove another point. My 73 yr old mother is on line now. She's using my old Dell laptop. I'll buy another low cost laptop, give the old ACER to her, and she will give hers to one of her grandkids. I will have a low end laptop that more than meets my needs, and hand down the old, which will still meet the needs of the recipient. No need to spend a 'grand'! [for my needs at least]
agl82
on Mar 6, 2010
gfryesc1, You are a complete scumbag. Drop dead. Sincerely, The Human Race
Waethorn
on Mar 6, 2010
@Doc: Don't forget: Old people have bad eyes. ;) Make sure the text size is nice and big, or buy a big external monitor to hook up to it and set the resolution LOW (or use a high DPI scaling option with a high resolution). I know some older folks that bought desktops (with big monitors) just because they couldn't read anything on any size of laptop. Monitors are cheap though. 22-24" ones should run less than $200US. Check to see what kind of monitor output your laptop has. Use a digital port if it has it (DVI or HDMI) for a sharper picture. A USB keyboard and mouse should run less than $30 for the pair too, and that way she has a full-sized keyboard and a real mouse instead of the trackpad. The laptop still does all the computing work, but it's portable, so if she still travels, she'll be able to take it with her. FYI: While an external monitor is hooked up to it, why not put the laptop BESIDE the monitor, open it up, and set the Windows desktop option to "extended desktop". That gives you option of using multiple monitors on a single computer. You have a laptop with a perfectly good screen there, so why not use it for extra desktop space for opening multiple windows and applications? I normally set the external monitor as the primary monitor. Windows (Vista and 7) is smart enough that when you disconnect the external, the built-in screen becomes the primary one, and it switches back when you plug the external back in. I use a laptop exactly this way. The smaller laptop screen is the secondary screen, and I can throw non-essential applications or windows over there for glanceable information. When I unplug everything, the laptop just acts like a regular laptop. FWIW: A lot of people never think about using a laptop in such a configuration. Most people think about only using an external monitor by itself (and perhaps just docking the laptop, closed), or mirroring the information on both screens. Completely O/T: I just found out the cavern is back open again: http://mystonline.com You'll be able to find me there from time to time.
tayme
on Mar 6, 2010
there != their --tayme
rr0de74@live.com
on Mar 6, 2010
Youtube is 70+% digital diarrhea of the mouth/worthless crap. Made more worthless with the in video ads now. The comments section should require a login just to read since its so full of human garbage and plain HATE. Of course I think Facebook is 90% digital diarrhea of the mouth, twitter 98%. But hey the hearing impaired can now fully partake in the joy of YouTrash. Google is not evil, they just want to rape your privacy and sell it to the highest bidder. I think only Facebook is worse than Google when it comes to privacy.
redunion1940
on Mar 6, 2010
Yeah but rr0de74 you have to admit there is a difference, Google builds a profile off of you on the web sites you visit to determine what ads to use against you, Al from what you do. With Facebook, you give them your information, one can't expect something bad not to happen when one does that.
Logjamming
on Mar 7, 2010
"Answer: 3 years later, and the iPhone is only 50% there." Right. Like the WinMobile 7 has multitasking. It hasn't. In fact, it's not even released. So, to put in your terms, some 40 months after the iPhone, Microsoft .. - (will probably) release on WinMobile OS that doesn't have multitasking, -has a Appstore that is filled with less apps than the final score in the icehockey final, -has departed from the business Winmobile business model that Steve Ballmer liked so very very much three years ago - will pay Thurrot and his sidekick Mike to promote it like it is innovative and 'what-the-world-needs' sort of blogposts - will keep the Microsoft apologists happy with an coolaid-drink called Courier. And, in the meanwhile, another container has been loaded with iPads, on its way to customers in three weeks.
DRWAM
on Mar 7, 2010
Wae, that''s exactly how I had the lappy set up in my office. Brilliant minds think alike. If she does well with this, I'll get her a desktop. Until then, I'll have my brother connect her old 19 in monitor since the laptop just stays in her bedroom on Ethernet. My wife is only 47 but needs reading glasses, but wants a laptop. She wants a big screen, so although I can increase font size, the 17in LED models are what I'll looking at for next XMAS. Back OT, the kids find more malware using Google search, but love the YouYube vids for teenie bopper music and Webkinz. However, we keep a close eye on the content. I know that there is a kids YouTube, but they don't always stay there.
chuckb84
on Mar 7, 2010
"What it actually does is allow Google to use those auto-generated text transcripts of the videos as a source of keyword tags that Google can attach to the profiles of everyone who watches each video." Bingo. I don't think Google is evil, but I have the opposite take from Paul on this youtube enhancement. The scary thing is that they have enormous POTENTIAL to be evil, and as Mike pointed out, they just increased their ability to figure out who you are and categorize you. The thing that scares me the most about Google, and Facebook, and all the rest that keep lots of info about you online is how they would react to certain types of subpoenas. Would they protect your privacy? How do you know? How would you know that the .gov had even made the inquiry? A friend of mine was happily using gmail, and sent a message (work related) that said something like, "I'm not going to simply parrot the position taken by others..." and then he started to get all kinds of ads from Google about tropical birds. He stopped using gmail. When the Israelis were surprised in the Yom Kippur war in 1973, their after action analysis emphasized that they paid too much attention to the supposed -intentions- of their foes and not enough to the -capability-. The capabilities that Google (and others) have for mischief is huge and quantifiable; their intentions are unknown and current promises and policies are no guarantee of future behavior. Again, I don't think Google is evil, but what COULD happen is very worrisome. Google is not alone in this; it's an issue that needs consideration along with all our happy talk of the future "in the cloud".

Please or Register to post comments.

IT/Dev Connections

Las Vegas
September 30th - October 4th

Paul ThurottYou'll have the opportunity to experience:
• 120 Technical
Sessions
• Networking with Peers
• Expert Speakers


Come See Paul Thurrott & Mary Jo Foley in Person!

Register Now

Office 365 InfoCenter

Get the latest insight and info from Paul

Read Now!

What I Use