Slashdot Mirror
Machine Translates Thoughts Into Speech
An anonymous reader points to this explanation of a brain-machine interface for real-time synthetic speech production, which has been successfully tested in a 26-year-old patient. From the article: "Signals collected from an electrode in the speech motor cortex are amplified and sent wirelessly across the scalp as FM radio signals. The Neuralynx System amplifies, converts, and sorts the signals. The neural decoder then translates the signals into speech commands for the speech synthesizer."
If my thoughts PORN HARDCORE PORN can be translated to text or speech by a machine BOOBS BIG BOOBS what is to stop our government from intruding?
...this tech is so cool, I'm speechless!
This article again? I've seen it blasted all over.
They keep referring to the patient in the test as a 'volunteer' but also state that he was "paralyzed except for slow vertical movement of the eyes." So he what? Signed the release forms by slowly looking up and down? I am guessing they mean volunteer as in 'his guardian(s) "volunteered" him'.
I judt got a nre Kinesis keybiartf so please excusr ant egregiou typos.
I am in office reading Slashdot, I like it!
Imagine the implications for people with cerebral palsy or paralysis of similar nature. I would always cringe when I watched someone who had been severely limited in their motor functions and could not speak, but with the help of an unconventional system, could communicate. They would stare at letters on a placard, and would spell out (at a rate worse than texting!) each word letter by letter. Or they would attach a rod to the forehead of the person and have them peck at a screen, again, typing out each word letter by letter. I get frustrated enough texting with one hand--these people have amazing patience.
There is a movie, based on a book based on a true story, called the Diving Bell and the Butterfly where this man gets into an accident and was thought to be in a vegetative state, but actually was fully conscious and aware of everything around him. This is called locked-in syndrome and it is scary to even imagine. He ended up being able to communicate with the outside world by BLINKING. And even blinking was difficult for him, since he only had control of one eyelid. The nurse would slowly speak out letters in order of the most frequently used (in this case, he was French, so the letters were in order of the frequency of letters in French words) and he would blink to indicate that this was the correct letter. Needless to say, this was a very long and tedious process. But, as a testament to the perseverance of the human spirit, he actually wrote a book sharing his experiences of being in this state.
Imagine the freedom he would have experienced at being able to talk again.
I really hope this becomes a reality.
My page.
He's pissed and he's all about enforcement.
Still I am sure he can be reasoned with.
H.
Imagine adapting this type of technology to other forms of input, such as a thought controlled dictation system. Imagine how much more someone like a Hawking could accopmlish.
I see you're of the "each letter only once" persuasion.
Pray for Mojo
I judt got a nre Kinesis keybiartf so please excusr ant egregiou typos.
English has about 20 vowels, but it only uses 5 or 6 letters to write them. This is part of the reason that non-native speakers find it hard to pronounce.
All I've ever wanted from brain-interface computing is the ability to 'think' music into some format where I can play it back again. Are we getting close to that yet?
TFA:Five years ago, when the volunteer was 21 years old, the scientists implanted an electrode near the boundary between the speech-related premotor and primary motor cortex (specifically, the left ventral premotor cortex). Neurites began growing into the electrode and, in three or four months, the neurites produced signaling patterns on the electrode wires that have been maintained indefinitely.
So the person using this had to "grow into" the electrodes and it took years to even get any kind of signal worth mentioning. And they haven't checked there aren't any short circuits between the electrodes caused by the neurite growth.
Three years after implantation, the researchers began testing the brain-machine interface for real-time synthetic speech production. The system is telemetric - it requires no wires or connectors passing through the skin, eliminating the risk of infection. Instead, the electrode amplifies and converts neural signals into frequency modulated (FM) radio signals. These signals are wirelessly transmitted across the scalp to two coils, which are attached to the volunteers head using a water-soluble paste.
So you're on the bus, your earbuds are deeply implanted into your ear canals and you're trying to avoid eye-contact, when all of a sudden you hear "I want to hump you doggy-style, oh, yeaah!" You look around the bus and notice a quadriplegic staring at you. You take your spare tin foil hat out of your pocket and put it on the lustful quadriplegic's head, saying to his 80 year old mother: "This hat goes really well with his wheelchair, doesn't it?"
How long or how many real or faked terrorist attacks will it take until such an electrode is mandatory and thoughts are registered and stored in central databases? Call me paranoid, but if something like this is technically possible it will be done. Of course, if not to prevent terrorist attacks then to protect our children. So the first to get this electrode will be sex offenders. The usual way to soften resistance against the removal of civil rights. True, the first versions now are still very primitve and not usuable for such a purpose, but compare the computers today with the ones twenty years ago.
That seems an unnecessary piece of anti-science paranoia. The people doing the experiment are not the white coated demons of science fiction. Even if they were as amoral as you suggest, it would sdtill be practical of them to get the patient's permission before starting an experiment that took over three years to set up.
On the radio recently, I heard about the difficulties the doctors had with an even more extreme 'locked-in' case that had no eye movement. They got the patient to communicate one bit at a time by imagining tasting milk or lemon juice for minutes at a time. This caused the patient's saliva to change pH. This was not simply "think lemons if it is ok to operate", followed by "oh, bother, best of three?" - they had to establish that the intelligence was present, understanding what was being said, and replying in a reliable manner.
There is a bit about milk-or-lemons and other attempts to communicate in... http://www.newscientist.com/article/mg19526171.500-humans-can-adapt-to-almost-anything-even-paralysis.html?full=true
There's an app for that.
"We live in a global world" - Harvey Pitt, former Securities and Exchange Commission Chairman
Most implant approaches use electrodes shoved in from the outside intending them to work immediately. That invasive technique leaves the person open to infection, and the neurons contacted tend to die fairly quickly, requiring yet another round of more of the same. This approach takes a long time, but eliminates the chance of infection (after the obviously necessary implantation) and lets neurons grow into and around the electrodes, so none of them producing signal are likely to die off soon, allowing long term contact and communication.
I'm sure there will be improvements on this, but this looks to me to be the first really viable direct neural signal collection technique.
"Five years ago, when the volunteer was 21 years old, the scientists implanted an electrode near the boundary between the speech-related premotor and primary motor cortex (specifically, the left ventral premotor cortex). Neurites began growing into the electrode and, in three or four months, the neurites produced signaling patterns on the electrode wires that have been maintained indefinitely.
Three years after implantation, the researchers began testing the brain-machine interface for real-time synthetic speech production. The system is “telemetric” - it requires no wires or connectors passing through the skin, eliminating the risk of infection. Instead, the electrode amplifies and converts neural signals into frequency modulated (FM) radio signals. These signals are wirelessly transmitted across the scalp to two coils, which are attached to the volunteer’s head using a water-soluble paste. The coils act as receiving antenna for the RF signals. The implanted electrode is powered by an induction power supply via a power coil, which is also attached to the head."
Rather than risking killing off speech center neurons in the implant process, they instead implant them in the pathway through which the speech center communicates outbound. Previous attempts by others went directly for the primary processing centers. This small change shows remarkable thinking foresight. I'd call this the first true hack in neural interfacing.
The only point of clarification I'd add is to say "through the scalp" instead of "across"; the latter more often implies a lateral vector. And the only point I'd request is, if only the scalp needs to be traversed, is the transmitter between the skull and scalp? It appears so but isn't stated s such in the paper (the PLoS article's URL is at the bottom of TFA). In any case, the FM transmission through the scalp does away with all the permanent jacks and sockets that SF and Hollywood have always used to signify brain/machine interfacing. With this one implementation, the future image of neural interfacing becomes something like a hair net with buttons sewn into it (we already have EEGs like this). Someone call Larry Niven. Wireheads will be buttonheads.
A future hack will almost certainly be to collect the signal wires running from the scalp to a second transmitter operating between the person and the machine. This will eliminate the direct connection and allow movement, including ambulatory data collection and processing. That not only makes possible testing in realistic situations, but also neural control of machine mediated locomotion for the paralyzed, without being restricted to the length of a cable. An obvious inclusion here would be a transmitter at the machine with receiver on the person, running the signals into the relevant muscle groups. This will also take some power induction that may be greater than the FM systems being used can handle. And are we not on the verge of getting wireless power induction for operating such devices, the same technology intended to refresh batteries and even run laptops?
A bit farther in the future will be to switch from spike analysis of neural firing to time/frequency analysis of synchronized activity such as EEGs examine. The former require computation that's commonly available. The latter require continuous wavelet analysis that s
"I may be synthetic, but I'm not stupid." -- Bishop 341-B
Actually, English has exactly 7 vowel letters. I learned this in first grade, why didn't everyone else?
A, E, I, O, U, sometimes Y, and sometimes W.
For example, Crwth, and Cwm. Look them up!
Actually, English has exactly 7 vowel letters. I learned this in first grade, why didn't everyone else? A, E, I, O, U, sometimes Y, and sometimes W.
For example, Crwth, and Cwm. Look them up!
Because those last two words are Welsh, not English. You could also argue that é is a vowel letter because of words like café, but of course these words are French in origin, even though they show up in English usage.
I wonder if this machine could somehow be used for military applications. If you'd make it accurate enough and hook it up to some transmitter device, you could use it for perfectly silent communications - sure, you have handsigns for that already, but words can be a little bit more precise at times...
A good education is a bit like a STD - it makes you unsuitable for a lot of jobs and gives you a desire to spread it.
I'm interested in the results of this technology as applied to stammering and similar speech disorders - these are not physical, but psychological issues, and appear to be mostly confined to the vocal chords; stammerers can type just fine. This might help us isolate exactly where the breakdown between mind and voice is happening.
What he can't kill, he has sex on. Trent.
We have it.
What he can't kill, he has sex on. Trent.
Also é isn't a vowel in French either. It's an accented variant of a vowel, that doesn't make it a separate letter in the alphabet.
French has A, E, I, O, and U, and Y is a "semi-vowel", at least that's what I was taught in grade school.
This
Not only does this device give people the power to send words directly to machines without physically speaking (or typing, our mousing). It was developed at the endpoints of the BAMA, the Boston-Atlanta Metropolitan Axis. Even the Buenos Aires corp gives the distribution a gibsonian unexpectedly exotic twist.
"Needn't speak out loud, miss... Subvocal's the way."
--
make install -not war
You clearly need an "escape sequence" :). e.g. you only switch to speech mode, when you think of something you've predefined as the "start" escape sequence. Then you get out by thinking of the "stop".
You could also have a "command mode", then that sends commands to the computer so that you can do stuff - then you get virtual telepathy and telekinesis.
Thought macros will help make things faster. Instead of thinking every little character of a command sequence, you'd use macros.
Translating your speech thoughts into speech by this machine requires implanting electrodes in your brain, wearing a large device stuck to your scalp, and then actually speaking (though this only reads your brain). If you do all that, the government can read your thoughts. Though the could read those speech thoughts with a microphone for a lot cheaper, and without your helping by going through all that surgery.
--
make install -not war
Basically she has bulbar onset ALS. Her main symptom is she can't talk at all anymore. You'd think just writing things down would be a appropriate substitute until you actually have to try it as your sole method of communication.
Did you know 80 to 90% of the moderators on slashdot wouldn't recognize a troll even if one dragged them under a bridge.
This is on-topic.
You just don't understand art...
8-P Bllll...
Stephen Hawking might be interested in this. On the one hand, I shudder at the risk to him, but on the other hand I wonder if he might consider the potential benefit worth it.
decide to charge you for thinking about their songs and decide that they want a broadcast fee...
Regards,
MBC1977,
Did anybody else suddenly think of daleks? Anybody? There's also the shellpersons from the Anne McCaffery novels.
We've already pioneered vision implants, tactile implants, and now finally speech implants so we're again at the forefront of cyborg technology.
"Bah!" - Dogbert
BTW, its technically possible to feed all human beings on earth, but I dont see that happening any time soon either.
It still is phonetically a separate vowel. The French language might have only 6 letters to write vowels, but the sound formed by e, é and è are so different they could be considered as different vowels.
Hmm... does /. has an automatic bot moderator? -1 based on filthy word, perhaps?
That would be Welsh, not English, surely?
Here is an AP story about the book (Appeared in the Kuwait Times). It was made into a piece of cinema.
http://www.kuwaittimes.net/read_news.php?newsid=MTMzMjY3NzAyMQ==
There has been controversy. There are claims that his amanuensis did much more than simply transcribe. I saw a squib on it somewhere. No link for that part of the story. But Google is your friend if you're interested.
"No fear. No envy. No meanness." Liam Clancy
...for safer air travel, if we apply this technology to all passengers. And, as we all know, air travel is voluntary, so please implant one of these in your skull and let us read your thoughts, or don't fly at all. Laugh about this now, see what happens in say... 20 years ?
Steeeeve.....
A brain interface is only as good as the number of unique states it can detect. I this case, it's only a handful (4 I think). So when the summary says "speech" it means "a number of vowel sounds." This guy isn't able to play the wheel of fortune, but he could buy a vowel - and that's about it.
Still, promising technology for sure. It just had a long way to go before fully synthesized meaningful speech.
or else!
No I dont think you can. Café is a French word that English speaking people use. I'm just glad English does not have an entire separate alphabet to wright words in that are non-English (see http://en.wikipedia.org/wiki/Katakana )
SQUIRREL!!!
Then here's a counterexample for humorous value, since you think you're good at being a pedant. Æ, Å, and Ø are all considered separate vowels in Norwegian, even though English speakers would see them as a ligature, an accented vowel, and "why is the empty set in the middle of this word?"
The long story short is that it's a bad idea to start trying to establish what counts as a vowel and what does not. Some maps of Proto-Indo-European suggest that r and l are vowels too, and there are even English words that use them as such—according to some definitions. It's all very non-concrete.
Exactly. People tend to forget that the analysis of a natural language necessarily comes after the language itself, and often mistake the descriptive system for a prescriptive one. Classification of language parts is useful, since it's easier to learn and remember things that are structured, but there will always be outliers and unsettled areas. The differences among described language systems highlight this.
Your brain is not a computer.