Gloves Translate Sign Language Into Auditory Speech 78
Zothecula writes about some pretty cool sensor gloves. From the article: "Since beginning in 2003, the Microsoft Imagine Cup has tasked students the world over with developing technology aimed at solving real-world problems. In this, its 10th year, students were asked to build their project around a specific Millennium Development Goal ... The winners have just been announced ... [and winning] first place (and US$25,000) in the Software Design category was the Ukraine's quadSquad with their EnableTalk gloves that translate sign language into speech in real time."
And thousands of interpreters stomachs sank (Score:2, Funny)
Re:And thousands of interpreters stomachs sank (Score:4, Informative)
Wrong translation direction, this going from signs to speech so a deaf person doesn't have to carry a txt2speech or a notepad and pen or learn to speak (yes deaf people can learn to speak, like one of my friends did, confuses the hell out of people who assume being able to speak means being able to hear)
Another thing is one of my kids former school teachers worked her way thru school in the opposite direction translating speech to signs. The general impression I got was it was much closer to the fry cook pay level than the $20 claimed above. You can get $20 if you have deep technical knowledge and translate tech docs from english to Chinese, or if you have a security clearance and know Arabic or other ME languages, but...
Re: (Score:2)
Re:And thousands of interpreters stomachs sank (Score:5, Funny)
So what would the translation be if you used the gloves to masturbate?
a a a a a a a a a a a a a a a a a a a a a a a a a a a a
Re: (Score:1)
So what would the translation be if you used the gloves to masturbate?
a a a a a a a a a a a a a a a a a a a a a a a a a a a a
In all honesty, it's closer to :
O O O O O O O O O O O O O O O O O O O O O O O O O O O
ps - My wife is an interpreter for the deaf
Re: (Score:2)
So what would the translation be if you used the gloves to masturbate?
a a a a a a a a a a a a a a a a a a a a a a a a a a a a
In all honesty, it's closer to : O O O O O O O O O O O O O O O O O O O O O O O O O O O
Well, that all depends on the size of the "ship," now doesn't it? Methinks thou art giving AC a wee bit too much credit in regards to the size of their dinghy.
ps - My wife is an interpreter for the deaf
That's pretty awesome man, no sarc. FWIW, one of my closest cousins is deaf, so I've learned quite a bit of sign language by proxy, although most of what he has taught me cannot be repeated in polite conversation...
Re: (Score:2)
Re: (Score:2)
being able to speak means being able to hear
A lot of folks I've met can't or don't want to do the latter . . . especially politicians and managers . . .
Re: (Score:2)
Wrong translation direction, this going from signs to speech so a deaf person doesn't have to carry a txt2speech or a notepad and pen or learn to speak
If you read TFA, it was designed for people "with hearing and speech disabilities".
Learning to speak is a big hurdle for many deaf people, but it is an insurmountable hurdle for those who are mute, even if they can hear.
Anyway. If you're going to wear a computerized glove that can speak for you, it seems that a chorded keyboard would be a much better choice. Faster, more accurate, and more expressive than an ASL translator.
Re: (Score:2)
That is not not something Ayn Rand was the first to state. It's even older than basic capitalism. For example, the ancient Greek and Romans knew that while slave labour was bad for the slave, it was essential for their society, and thus a net-gain for it.
But as you can quite clearly see, whether a net-gain for society is morally good or wrong depends on what kind of society you are talking about.
And then of course, the windowmaker-fallacy is also not very far away. Just because you break a window and give a
Old News... (Score:5, Funny)
Re: (Score:1)
Re: (Score:1)
Amy, good Gorilla. Amy pretty. Amy love you.
This is immediately what I thought of when I read the headline as well!
Obvious...after you see it (Score:2)
Re: (Score:1)
Re: (Score:2)
Or just into words? Most people that understand sign language also understand written language.
Re:Obvious...after you see it (Score:5, Funny)
With that kind of glove, deaf people could say "Talk to the hand, because the ear's not listening!"
Re: (Score:2)
Re: (Score:3)
So, this device only actually allows the signer to sign letters that can be used to spell words, rather than translating full words and phrases.
If that's all they were going for, then I already have a tried and true set of devices that allows for the two-way communication you're talking about, and it's far cheaper, to boot.
Paper and pencil.
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
From TFA: (Score:1)
"Although the software was developed under Windows Phone 7, the team was forced to turn to the older Windows Mobile platform for their entry because Windows Phone 7 doesn’t provide developers access to the Bluetooth stack, which is how the gloves communicate wirelessly with a mobile device running the translation software."
And that tells me all I need to know about WP7!
No, it translates fingerspelling into speech (Score:5, Insightful)
After watching the video, it seems that what they've done is create gloves which recognize the various fingerspelling signs. If somebody wants to sign "I need to withdraw money" (like, at a bank), what this allows them to do is to make the sign for "I", then "N, E, E, D", then "T,O", and so forth. Then the gloves feed that output into a TTS system. This works (because ASL users and English speakers share a writing system), but is horribly inefficient, and would be equivalent to a translation module that makes you speak every letter of the written words individually before putting the words into Spanish.
This is fundamentally different from "translating sign language", where the gloves would recognize the (much more complex and spatially oriented) sign for "I", for "need", for "withdraw" and for "money", and then translate that into "I need to withdraw money" and speak it aloud. Adding in the fact that ASL syntax is fundamentally different than in English, it's quite a tall order. Interpreters need not fear.
This is cool, nobody's denying that, and for some jobs, this might be great, but at the moment, I don't see it working much faster than taking out the requisite smartphone and writing down what you're trying to get across.
Re: (Score:2)
Finger Spelling is NOT Sign Language (Score:5, Informative)
Mod parent up! Finger Spelling is *not* Sign Language. If all this does is translate finger spelling into synthesized speech, the same thing could be done much faster and cheaper by just typing the words on a standard smartphone device.
This is not even cool. It is just, plain, wrong in so many ways. All of the money and hype spent making and marketing this device would reap 10X as much benefit if the same money were spent educating people about the real nature of deafness and sign language. The developers of this waste of time could start by taking a class about deafness themselves.
The fact that Slashdot perpetuates the inaccurate headline equating finger spelling with sign language just demonstrates how ignorant we all are.
Re: (Score:1)
And the next question is... which finger spelling language are they translating? American? Irish? British? Australian? International (a mish-mash of English finger-spelling systems) ... every language uses a different set.
Re: (Score:3)
Re: (Score:2)
Re: (Score:1)
Re: (Score:3, Interesting)
After watching the video, it seems that what they've done is create gloves which recognize the various fingerspelling signs. If somebody wants to sign "I need to withdraw money" (like, at a bank), what this allows them to do is to make the sign for "I", then "N, E, E, D", then "T,O", and so forth. Then the gloves feed that output into a TTS system. This works (because ASL users and English speakers share a writing system), but is horribly inefficient, and would be equivalent to a translation module that makes you speak every letter of the written words individually before putting the words into Spanish.
This is fundamentally different from "translating sign language", where the gloves would recognize the (much more complex and spatially oriented) sign for "I", for "need", for "withdraw" and for "money", and then translate that into "I need to withdraw money" and speak it aloud. Adding in the fact that ASL syntax is fundamentally different than in English, it's quite a tall order. Interpreters need not fear.
This is cool, nobody's denying that, and for some jobs, this might be great, but at the moment, I don't see it working much faster than taking out the requisite smartphone and writing down what you're trying to get across.
I work with a deaf person, and believe me, they can sign incredibly fast. I reckon that he could say something simple "do you want to get lunch" fast enough with finger spelling that it'd sound completely normal speed to me. Sure, adding memory for all the words for various languages would be neat (very hard though), but for now, it's quite useful. Keep in mind that they don't always carry paper/phones with them, so sometimes the only option is to sign.
Re: (Score:2)
Finger spelling is not how ASL normally works though.
Think of even simple phrases like "thank you" no finger spelling involved.
If they have to carry this device to finger spell they might as well use the phone it is connected to type out the message. If they are not carrying anything than this device would do them no good.
Re: (Score:2)
Re: (Score:2)
You are right in every aspect, but you also have to factor in that this is was merely a student project. It serves extraordinary well as proof of concept. Now someone (perhaps MS?) needs to focus on it and improve it by making it able to translate the actual sign language gestures. If fingerspelling is possible, the jump to sign language should be not that hard.
Re: (Score:2)
where the gloves would recognize the (much more complex and spatially oriented) sign for "I"
Actually, the sign for "I" and the sign for the letter "i" are pretty much identical... but your excessively intensified and outrageously exaggerated point is well taken.
Re: (Score:3)
Only if they spell out each word, which is not generally what ASL users do. Even many phrases, my limited knowledge of includes "Thank You" which is one motion, not spelling out the words.
Re: (Score:2)
This actually does solve a real world problem
Use case?
Re: (Score:2)
It very much DOES, just not in the most efficient way.
while this may have limited to no REAL value at the moment, there were a LOT of saying the EXACT same thing about the internet in 92-94.
You naysayers might want to think about that.
Re: (Score:2)
I just want to know the use case. What if it were perfect and could precisely translate sign language into spoken or printed English - what advantage would it hold over a keyboard or smartphone or even a pen and paper? Plus, many (most?) deaf people can speak.
Re: (Score:2)
Maybe your mute? you can't speak. sign language (real sign language) is much faster then typing or writing from what I understand. Wear the gloves leave your phone in your pocket, wear a small speaker around your neck. You look fairly normal standing at the bank instead of like a freak waving a clip board.
keep in mind to do sign language, you don't need to be able to see your hands like with typing. you don't have to fish a device out your pocket every time you want to talk...
It would be perfect for any sit
Re: (Score:2)
You are right I suppose - if they could get it to do more than just simple letter signs (which are slower than typing). And if they could get it to translate sign to English. And if you could still use your hands while wearing the gloves.
But I gotta tellya, when stuff like this is happening [msn.com], the uses for something that depends on exaggerated hand motions seems to diminish :)
Re: (Score:2)
Maybe your mute? you can't speak. sign language (real sign language) is much faster then typing or writing from what I understand.
If true, this is the really interesting part. If signs could be interpreted like typing, but faster, the gloves would replace keyboards in a way that voice-to-text can never do, even if done perfectly.
Why not just use a cellphone? (Score:2)
With a text to speech app?
Re: (Score:2)
With a text to speech app?
Presumably because it's faster to sign than it is to type, in much the same way as it's faster to speak than it is to type.
Re: (Score:3)
Re: (Score:2)
With a text to speech app?
Presumably because it's faster to sign than it is to type, in much the same way as it's faster to speak than it is to type.
Indeed, it is.
Unfortunately, the glove does not translate sign language, but rather transcribes finger spelling.
In this case, the text-to-speech app would be superior.
Not going to work (Score:5, Informative)
'Real' sign languages (like ASL) are much harder to translate because they are somewhat non-linear. A single gesture can describe several things at once: size, direction, emotional state, etc. There's no way you can translate it without fully understanding the context of the speech. And we all know how good computers are at such tasks...
Re:Not going to work (Score:5, Interesting)
Also ASL does not have articles, so it does not translate directly to english. It is really a visual spatial language, people always seem to miss that.
"Auditory Speech" (Score:1)
Re: (Score:2)
Olfactory Smelling.
I am anosmic, you insensitive clod!
(btw, I really am anosmic, a smelling device would be awesome :p)
Re: (Score:1)
^ This is exactly the kind of post /. will be filled with the day transporters or flying cars are actually built.
Done over 25 years ago. (Score:2)
A grad student at Stanford at the Center for Design Research did this in the mid-1980s. It had to be connected to a workstation back then, of course.
Car analogy - well sort of (Score:2)
Re: (Score:2)
Re: (Score:2)
FYI, it's = it is. ..!.. too. :P
If the alphabet is all there is to English... (Score:2)
Then I guess it translates sign language. Finger-spelling is just an alphabet. I don't know about other sign languages, but ASL is a full language with its own grammar and conventions, and it would take a lot more than a glove to interpret it. Positions of hands with respect to the body are important, as are facial expressions, and ASL's pronoun system is largely spatial with the handshape only indicating the type of pronoun (e.g. personal vs. possessive). Even if a piece of technology could reliably capt
Re: (Score:1)
And it just translates American Spelling Alphabet (French). Which is mostly one handed spelling.
It would bomb horribly trying to understand any British (English) based finger-spelling, which is two-handed. http://en.wikipedia.org/wiki/File:British_Sign_Language_chart.png [wikipedia.org]
Re: (Score:2)
While I suspect that was a joke, in theory Kinect would actually be a better platform upon which to build an ASL-to-English translator, if not for the fact that the skeletal data it provides does not include fingers.
Re: (Score:2)
And the fact that you'd need to wear some kind of exoskeleton that mounts the sensor far forward of your body, so it can see what your hands and arms and face are doing.
Mobility is the point here. If you can sit at a computer, you can just type instead.
Of course you can just type on a smartphone too, without wearing a freaky bulky obtrusive glove. But others have already mentioned that.