Slashdot Mirror
Microsoft Research Uses Kinect To Translate Between Spoken and Sign Languages
An anonymous reader writes in with a neat project Microsoft is working on to translate sign language with a Kinect. "Microsoft Research is now using the Kinect to bridge the gap between folks who don't speak the same language, whether they can hear or not. The Kinect Sign Language Translator is a research prototype that can translate sign language into spoken language and vice versa. The best part? It does it all in real time."
Kinect translation with new autocorrect-for-ASL: "I really like your tits"
Thanks Microsoft!
Sent from my ENIAC
How do you sign: Dear aunt, let's set so double the killer delete select all?
Required reading for internet skeptics
... flipping the bird?
some signs need no translation.
Sent from my ENIAC
... I flip the bird does is say FUCK YOU ??
There's a lot of contextual clues necessary to understand sign language. Most conversations would seem "faux caveman" like to the outsider - a lot of Noun Verb Noun going on...
I'm going to have to watch the video from another machine, but I'm more interested in the bumper at the bottom that has realtime English/Chinese translation in your own voice...
We were doing real-time ASL translation to text using the webcam on the Indy2 workstation back in 1997, success rate was about 85% and most of the misses were from hidden object problems which the Kinect does nothing to help with.
There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
I'd love to see a blind person try to use touch screen phone.
There's no -1 for "I don't get it."
As far as ways to communicate online goes, I'm not sure how useful of a tool this would be. I can definitely see how this could easily become the best way to learn sign language though if paired with Rosetta Stone-like tutoring software. My wife has been planning to learn sign language soon, I'm sure she'd love to have something like this as a learning aide.
Not just text messages, but also online college courses, Facebook messages, etc. Especially for people like me who are deaf enough that suffer a lot - socially, academically and in the workplace, but not so deaf that we qualify for any sort of assistance. It's a shame Obamacare doesn't address hearing aids and glasses, it would have likely gotten a lot more support.
You clearly haven't seen two or more deaf people in public.
Plenty of people sign. Heck, plenty of hearing people sign.
Conversations (deaf-deaf, hearing-hearing, hearing-deaf) are all much more natural face-to-face where you can interrupt, show expressions, assign nuanced gestures or tones to words -- all things that are not well suited for text.
I tried to tackle the same thing a couple of months back using OpenCV and a smartphone. Before starting I consulted with people that knew sign language and the problem is not so much recognizing hand gestures, but facial expressions. They say that most of the conversation happens with a a given look, a frown, or the movement of the lips.
Needless to say, I though it was too hard to solve the problem on a smartphone so I postponed the project. I don't think Kinect can do a much better job at picking up the small details of facial expressions, but let's wait an see.
never underestimate what people can do
http://appleinsider.com/articles/11/09/15/stevie_wonder_thanks_steve_jobs_for_making_ios_devices_fully_accessible
Goodbye Apple and Google. This technology is set to put you OUT. OF. BUSINESS.
If the kinect is tracking your arms/legs/fingers/head etc. I'm fairly certain it can be programmed to start using facial expressions to add the missing conversations.
Looks like about the quality of verbel speech recognition...
I have never seen anyone sign that clearly or slowly except to very new beginners.
I'd love to see a blind person use sign language.
"" How about taking the safety labels off everything, and let the stupidity-problem solve itself? """
Yup. Many signed phrases are just noun, verb, point, noun .
They do. They use iPhones (and iPads). iOS has an accessibility feature called VoiceOver which changes the input paradigm from a touch initiating a 'click' action to one where a touch reads out the description of the UI element with text-to-speech. Two taps on the item will send a tap to the UI, and a three-finger swipe will initiate scrolling. So you can basically drag your finger across the screen and find things with your ears instead of your eyes, then navigate and interact as a sighted person would once you get your bearings.
It's a shame Obamacare doesn't address hearing aids and glasses, it would have likely gotten a lot more support.
That's funny. Not only is the deaf community a tiny minority (unlikely to have any impact at all), the issue of hearing aids is enough to divide them! If they found out you could get a cochlear implant with insurance purchased through an exchange, you'd see little other than opposition. (Yeah, they're that crazy.)
Not that they're likely to be aware of the issue, as illiteracy is so prevalent. Still, if they found out, they'd oppose it.
Required reading for internet skeptics
This is one of the stupidest things I've read all day. You think that pupils at a school for the deaf are sending each other text messages as they stand next to each other? Signing is still very popular among the deaf, and is even a part of the distinct culture that has arisen in deaf communities.
Your comment shows the sign of ignorance. Plenty of deaf AND hearing people sign anywhere. It's easily 10 times faster than texting. Even faster than speech itself.
Yeah, trippy that the Deaf want to protect being Deaf so much that they don't want other deaf people to hear!
Spot on. Also, sign language is quite important culturally as the native language of deaf people. All cultures view their native language as essential to their cultural identity. The deaf are no different (or so I hear.)
Possibly obsolete, but it's spawned at least one mini-celebrity.
Except sign is a con lang -- strike that -- a bunch of different con langs incompatible with one another.
Required reading for internet skeptics
Deaf culture is destructive.
Required reading for internet skeptics
I have two deaf cousins who would beg to differ, and all of us in the family who learned to sign can communicate much quicker by signing than grabbing a smart phone. And my hands do not need electricity. Fucking douchebag.
The Revolution Will Not Be Televised
Can't tell if that's intended to be a troll or not. Since this is the internet I have to assume it is.
As far as trolling goes, being married to a deaf women I'm pretty pissed off at it. It's so rude and dead wrong I'm left incredulous, but that is the point of trolling isn't it.
Have... Have you heard of Helen Keller?
You'd see them hold their hands around the person signing to them, so they can feel the gestures. This is one of several techniques.
You do not have a moral or legal right to do absolutely anything you want.
I'd love to see a blind person try to use touch screen phone.
Touch screen phones may well be the best tech to come along for helping blind people ever.
http://bits.blogs.nytimes.com/2013/09/29/disruptions-guided-by-touch-screens-blind-turn-to-smartphones-for-sight
Since that might be pay-walled, here's a copy:
Disruptions: Visually Impaired Turn to Smartphones to See Their World
September 29, 2013, 11:00 am
In recent years, many smartphone apps that are aimed at blind people have appeared.
Luis Perez loves taking photographs. He shoots mostly on an iPhone, snapping gorgeous pictures of sunsets, vintage cars, old buildings and cute puppies. But when he arrives at a photo shoot, people are often startled when he pulls out a long white cane.
In addition to being a professional photographer, Mr. Perez is almost blind.
"With the iPhone I am able to use the same technology as everyone else, and having a product that doesn't have a stigma that other technologies do has been really important to me," said Mr. Perez, who is also an advocate for blind people and speaks regularly at conferences about the benefits of technology for people who cannot see. "Now, even if you're blind, you can still take a photo."
Smartphones and tablets, with their flat glass touch screens and nary a texture anywhere, may not seem like the best technological innovation for people who cannot see. But advocates for the blind say the devices could be the biggest assistive aid to come along since Braille was invented in the 1820s.
Counterintuitive? You bet. People with vision problems can use a smartphone's voice commands to read or write. They can determine denominations of money using a camera app, figure out where they are using GPS and compass applications, and, like Mr. Perez, take photos.
Google's latest releases of its Android operating systems have increased its assistive technologies, specifically with updates to TalkBack, a Google-made application that adds spoken, audible and vibration feedback to a smartphone. Windows phones also offer some voice commands, but they are fewer than either Google's or Apple's.
Among Apple's features are ones that help people with vision problems take pictures. In assistive mode, for example, the phone can say how many heads are in a picture and where they are in the frame, so someone who is blind knows if the family photo she is about to take includes everyone.
All this has come as a delightful shock to most people with vision problems.
"We were sort of conditioned to believe that you can't use a touch screen because you can't see it," said Dorrie Rush, the marketing director of accessible technology at Lighthouse International, a nonprofit vision education and rehabilitation center. "The belief was the tools for the visually impaired must have a tactile screen, which, it turns out, is completely untrue."
Ms. Rush, who has a retinal disorder, said that before the smartphone, people who were visually impaired could use a flip-phone to make calls, but they could not read on the tiny two-inch screens. While the first version of the iPhone allowed people who were losing their vision to enlarge text, it wasn't until 2009, when the company introduced accessibility features, that the device became a benefit to blind people.
While some companies might have altruistic goals in building products and services for people who have lost their sight, the number of people who need these products is growing.
About 10 million people in the United States are blind or partly blind, according to statistics from the American Foundation for the Blind. And some estimates predict that over the next 30 years, as the vast baby boomer generation ages, the number of adults with vision impairments could double.
Apple's assistive technologies also include VoiceOver, which t
When information is power, privacy is freedom.
No, it isn't. Some (all?) modern sign languages may have begun as attempts as constructed languages for the deaf but they quickly creolize just like any other natural language. In fact there's evidence that sign languages are older than spoken languages. For one, young children can acquire sign language younger than they can acquire spoken languages partially because the hand movements are a lot easier for young children than learning to use their vocal cords.
There are lots of research being done with kinect, by BS and masters students, mostly around physiotherapy. This is one of those creative applications that everybody says after hearing about it .. "damn, why didn't I think of that". Very creative use of the kinect.
Well... sending each other texts while standing next to each other works for non-deaf teens....
it is quicker and more convenient for the disabled to send a text message.
I would have thought it would be more convenient for someone to speak/be spoken to in their native language - sign - rather than send/receive a text in a foreign language - English or whatever.
Esli epei etot cumprenan, shris soa Sfaha.
No, and neither has she.
Looking at the video in the article, it seems that "in real time" means "at about 1/4 of the speed of regular signing".
Imagine. Having. To. Speak. Like. Kirk.
Esli epei etot cumprenan, shris soa Sfaha.
This is one of the stupidest things I've read all day.
Awfully generous of you to use "day."
Not sure how ASL compares to BSL (I'm a BSL n00b), but facial expressions are one thing that has bothered me about sign-to-text/speech systems. Without facial expressions: I can't express the magnitude of certain things; I can't ask questions; I can't answer some questions; I can't distinguish between things like uncle, aunt, nephew, niece or battery; yadda yadda. Non-manual features are really important grammatically and expressively.
There are also signs that don't really have an equivalent in spoken/written language unless you start incorporating diagrams into the translation.
Don't get me wrong, I think work like this is a great idea but the projects I've seen so far either ignore the problem or grossly simplify it - losing the power and expressiveness of sign language.
They do. My friend did a article about that. She spend one week with a couple who both are deaf and the man had become blind few years before.
They both communicate with sign language but it is done by holding each other hands when doing it. There were three couples registered to be in same situation that they need to communicate with physical sign language.
You can be amazed what people can do who can not hear, talk and don't have anymore capability to see. They live normal live just together.
ps. My friend is deaf as well, can speak pretty well if really a required but she doesn't like to do it because it is really hard to her to speak more than few words.
Because that's not so much about being "deaf" per se, but really about ASL culture....Like many linguistic minorities, they often perceive themselves as under attack.
People who are functionally deaf are a minority (less than a million in the US), and hearing aids will likely never help them. People who are partially deaf and would benefit from hearing aids are thought to number at least 10 million in the US, and that may be a low estimate. To put it in comparison, there are only 7 states with more than 10 million residents (and three of those aren't too much higher).
There's also a lot of people with partial hearing loss who do not identify with any "deaf community". I recognize that it exists, but equating hearing loss with being part of the deaf community is just plain wrong.
That's generally a vocal minority that's mostly perpetuated by the older population that has always been deaf. Deaf people who aren't exposed to the older deaf generation are much more open minded. Unfortunately, some colleges aimed at the deaf (I'm looking at you, RIT NTID) continue to perpetuate this - as a result, many students there come to equate deafness with being an asshole. And I don't blame them.
(or so I hear.)
Now that was fucking funny.
Disclaimer: yes I work for Microsoft. No not on these projects.
This was demo'd live in front of 30K MSFT employees at our annual company meeting. It nearly brought me to tears. Yes, I can see through demoware and and yes it's highly imperfect, but honestly it was the single most impressive use of technology I've ever seen. It was both novel and simple. It combined hardware, algorithms, user experience, and cloud scale. I don't know if it will ever go anywhere though I expect that it will. The key point here is that these are off the shelf components. Kinect and gesture APIs combined with machine translation and text to speech. It's important that these are, all or nearly all public production APIs. Such a system 10 years ago even if possible, would never make it to market because of the tiny user base. Today we can build such apps for the 0.01% of the population that need Mandarin Sign Language translated to English. And it can be cost effectively. That is the point. Technology being used to address real problems for under served communities. So yes, maybe people researched automated sign language recognition years ago, but bringing it to market and enabling a scenario for real people is a wholly different beast
Yeah, I've found that presenting the proper (or improper) finger while driving is much faster than yelling "F- off" out the window.
Slow down, cowboy! It has been 4 hours since you last posted. You must wait another few hours.
I knew it! the Federation runs on Microsoft technology. Guess that explains all the exploding consoles and Transporter accidents.
I've got better things to do tonight than die.
The ASL interpreters I know do a lot of on-call work for medical, mental health and educational purposes. One thing they mentioned is ASL has regional dialects.
Ask and ye shall receive: http://www.youtube.com/watch?v=qoClCdxaUCk
Ask and ye shall receive: http://www.youtube.com/watch?v=c0nvdiRdehw
They (I assume the same group) demoed the real-time English/Chinese translation in your own voice last year. It's really impressive, and the results were surprisingly good.
I do wonder how it deals with phonemes that are present in one language but not in another, maybe there's a "training process" you have to do initially to make sure it has enough recorded samples to get full-coverage of the target language.
Comment of the year
Blind people can (usually) speak and hear just fine so they aren't particularly relevant to a discussion about sign language which is a solution for deaf or mute people.
For blind people we have speech to text and text to speech technology. Not much point involving sign language in there as it'll juts make things more complicated.
nods and looks sad, grabs cap brim with left hand and runs right thumb along chin
Sent from my ENIAC
UNlikely.
Much subtler changes for facial work.
Sign comes in handy in very noisy environments, or conversely where silence is golden. Then there's job-specific signing, as for crane operators and their spotters.