A 16-Year-Old Builds a Device To Convert Breath Into Speech 67
stephendavion writes A 16-year-old from India has designed a device that converts breath into speech. High-school student Arsh Shah Dilbagi invented TALK as a portable and affordable way to aid people suffering from ALS, locked-in syndrome, and anyone else speech-impaired or paralyzed. Prototyped using a basic $25 Arduino microcontroller, Dilbagi's invention costs only $80, or about a hundred times less than the sort of Augmentative and Alternative Communication device used by Stephen Hawking. TALK works by translating breath into electric signals using a MEMS Microphone, an advanced form of listening tech that uses a diaphragm etched directly onto a silicon microchip. The user is expected to be able to give two distinguishable exhales, varying in intensity or time, so that they can spell words out using Morse code.
So.... (Score:3)
Re: (Score:2)
Re:So.... (Score:4, Interesting)
I don't know. How many words can the average person speak before they pass out? It seems like a similar type of breath control. I just sat here and tried some "Morse code" breathing through my nose and it seems like a perfectly legitimate solution to the problem. With practice, I bet a person could communicate pretty quickly this way.
Re: (Score:2)
IP Stolen (Score:3)
I say that as if I know it has already happen but I am fairly sure that the guy will never see any return from his invention.
Re: (Score:3)
Re:IP Stolen (Score:5, Insightful)
It darn well should be about the money.
People like this, true innovators, should be showered with money so they can keep coming up with stuff like this.
Re: (Score:2)
Your probably right but so what?
Unless your saying we should keep innovators poor just in case they get lazy (a ridiculous argument) your point is redundant.
Re: (Score:2)
Come on. It's simple. "You're"="You are". You can do it. I know you can figure it out.
Re: (Score:2)
It is simple for most I suppose but dyslexic people like myself really struggle with it.
Re: (Score:2)
Re: (Score:2)
Re: (Score:1)
Training the machine to read each individual's brain signals and teaching the affected individual (who can't talk to you easily, remember) would take a lot more time than teaching the affected individual morse code
Finally, fMRI machines (non-invasive way of reading the brain signals) are really expensive, and brain surgery to implant electrodes to read the signals directly is both incredibly expensive and incredibly dang
Re: (Score:2)
Re: (Score:2)
Stephen Hawking can only communicate at about 1 word per minute. Using morse code may be slow compared to speaking, but it still could represent a pretty substantial improvement for some people.
Re: (Score:2)
I don't think morse code practical in this case, unless the "speaker" wants to communicate in short words and sentences. Verbal English can consume 2-3 letters at a time, whereas morse code can require up to 3-5 dots/dashes per letter. It's a very slow medium. For example, just saying "No" requires 4 dashes and 1 dot; "yes" requires 3 dashes and 5 dots.
What would you recommend? Morse is well understood and standardized in many contexts like HAM radio. Perhaps an adapter that can the breaths and turn them into phonemes that then get converted into text? A cloud NLP application tying into such a device (simple as querying Google with the output and seeing what it suggests) could result in some very useful (and maybe even tailored) responses.
Just wondering, though, how would backspaces be handled...
Kudos! (Score:2)
I congratulate this kid for thinking outside the box. I wonder where he will go from here with his invention?
I have a friend who was recently diagnosed with ALS, and the disease is progressing agressively with him. I hope there is something affordable like this when and if he gets to the point he needs it.
Re: (Score:2)
And given the fact that Medicare is aggressively pushing to make augmented communications devices rentals (and something that you can't take to the hospital with you), if it's really $80, then GO FOR IT.
Hopefully the hardest part is teaching the victim Morse.
Re: (Score:2)
Tied to a video display, which would take much more sophisticated development, it might be easier. It's a fascinating idea for people like Stephen Hawking, or as a fall back device for people whose more sophisticated tools may need repair.
I hope that this youngster talks to Lady Ada, over at http://www.adafruit.com/ [adafruit.com], about publishing a do-it-yourself kit for this.
Bad language (Score:1)
about a hundred times less than
Don't ever use this phraseology. It's meaningless.
N times more than == N+1 times as much as, but "N times less than" isn't anything.
It might seem intuitively true that "2 times less than" would be "half as much as", but then what is "1 time less than"?
This is stupid.
Re: (Score:2)
No you are just reading it wrong.
So if I have a bit under a liter of water, I have "100 times less than 10 mL" because I know it is less than 10 mL that I have 100 of. Makes perfect sense to me. So what they are saying is, the device Stephen Hawking uses costs less than 1/100th the cost of this, or a bit under 80 cents.
I had no idea Stephen Hawking's devices were so cheap! Thats amazing, I am shocked this was even created now!
Re: (Score:2)
Is it just me or does it seem like this could have been done a half century ago?
Non-MEMS Microphone -> Op Amp -> PID controller -> Buzzer
I actually don't understand what benefit is gleaned from using a MEMS microphone instead of an ordinary condenser one.
Size and price?
Re: (Score:2)
Perhaps the ability to pick up the sound without outside interference too? Or the fact that the MEMS creates more or less a digital signal by default?
Actually, it likely isn't doing anything with sound in the traditional sense. The MEMS microphone is pressure sensitive so it is likely not listening for breathing but measuring pressure differentials when breathing occurs. This could aid speed because you could close your lips and move your tongue or mouth or even flex your throat to force air through your no
I invented one of those years ago... (Score:1)
I invented one of those years ago when I was just a babe, I call it a larynx. I wish I had thought about patenting it...
Re: (Score:2)
The fancy ones are expensive.. (Score:3)
..because a lot of design work has gone into them, and they have more stuff that makes them more usable.
Off the top of my head, I think this device would be slow to use, and would require a fair amount of skill/education (you have to be able to spell words in morse code - fine for many, but a problem if you've got broad developmental issues). Physically, for many users, taking 15 breaths to spell a word is going to be slow and (for some) very tiring. As you get tired and aren't in perfect control of your breathing, even small errors in input would cascade down and the resulting words would be unintelligible. Because Morse code isn't actually well suited to the task.
Again, off the top of my head, it seems like it'd be much faster to choose common words (or pictures) off a screen (a screen wouldn't add much to the cost - probably only a few dollars). Then you could use continuous breaths - perhaps with the device measuring breath velocity when the user is able to moderate that - to alternatively move a cursor x+y (and then a short breath to "click") to choose options off a grid. With some training, I bet you could get most common words in 3 breaths this way. Or, when more choices are required, you could use the same mechanism to press keys on a keyboard (though, again, you'd definitely want word completion). For heavy users without developmental issues and with good breath control, you could build out a shorthand type system that might be fast enough for reasonably paced conversation (using breath length/intensity, and lengths of pauses between).
I'm not saying this isn't a cool thing, and it could certainly be made cheaply (though, again, a very cheap screen would make this a lot easier to use). But it's pretty much the "hello world" of assistive devices. I like when people make new things, and I like effort/attention going to problems like this, but I'm tired of how these articles tend to belittle the work done by others who've approached the same problem. It's not that nobody ever thought of making a simple breath control system before. Most likely everyone who approached the problem started by making a device much like this to test the initial breath control... and then they made fancier ones that worked better, based on the feedback they got from real users. Pretty much any suitable engineer, when presented with this problem and a cost constraint, would be able to make a similar or more usable device.
That's no disrespect to him (he's doing a good thing) - it's disrespect to this kind of breathless reporting. No, some teenager in Britain didn't come up with a way to triple the speed of your internet connection. No, some science fair kid didn't come up with a way to make solar panels 100% more efficient. People seem to love the base story here (teenager shows us all the way), but the stories almost always well overstate their case.
Re: (Score:2)
That's no disrespect to him (he's doing a good thing) - it's disrespect to this kind of breathless reporting.
What was that? Tasteful? ;)
Re: (Score:2)
Lol yeah - I get that. What I'm saying is blowing out letters in Morse code isn't the most efficient way to communicate, even when we restrict ourselves to using breathing.
Re: (Score:2)
Re: (Score:2)
I'm not sure you're wrong - I've never used one of these. The only similar devices I've seen used were based on gaze (which is obviously a different animal).
But to be clear, I would do this as an x-y grid - so there'd be an x-blow and they a y-blow, then either a click or more blows to correct (which I don't think would be necessary often with some practice). And, also to be clear, you'd often be picking words/phrases/actions rather than individual letters. I don't know the best potential scheme - but wh
Re: (Score:2)
Re: (Score:2)
If you could differentiate between lots of breath strengths, I suppose you could have up/down/left/right. But it might be easier to just alternate (ie. you do a right breath, then a down, then a right). You could do stronger breaths to start/do big movements, then proportionally little breaths to fine tune your position. Again, I think with some training you could hit targets pretty well with few breaths (assuming you have good proportional control, which might require a different sensor than a microphon
Re: (Score:2)
the fancy ones are $8,000 instead of $80 is because IP laws protect monopolies. in an open ecosystem where everything is free as in libre, any person designing medical devices could interoperate with everyone else designing medical devices. ever call to every piece of hardware would be workable by anyone who wanted to. every program even one privately funded, would then be opened to the community so their competitors could learn what you did and how and be able to build on what you did.
and if that smells li
Re: (Score:2)
>> the fancy ones are $8,000 instead of $80 is because IP laws protect monopolies
Wrong. The fancy ones are $8000 because they take a lot of engineering work to develop and the market is very small. If you want to recoup your investment you have to sell it for a high price.
The rest of your comment is just fancyful nonsense.
A hundred times less? (Score:2)
Sure if thing A is inexpensive, then thing B which costs a fraction of that price might indeed be said to cost X times less. Implying that thing A is already less than some other option, and thing B is even MORE less.
But if thing A is very expensive (as in the example cited in TFA), thing B would be better described as being not a hundred times less
As a regular at the Mosque (Score:2)
As a regular at the Moosque I'd rather be interested in the opposite device converting speech into breath.
Helmet (Score:2)