Machine Translates Thoughts into Speech in Real Time

Right on the tails of this, comes this:

  Quote

By implanting an electrode into the brain of a person with locked-in syndrome, scientists have demonstrated how to wirelessly transmit neural signals to a speech synthesizer. The "thought-to-speech" process takes about 50 milliseconds - the same amount of time for a non-paralyzed, neurologically intact person to speak their thoughts. The study marks the first successful demonstration of a permanently installed, wireless implant for real-time control of an external device.

http://www.physorg.com/news180620740.html/r:t/

The future is moving fast...

PS: This would make a fun midi controller.

  On 12/26/2009 at 7:19 PM, chaosmachine said:

The future is moving fast...

 

PS: This would make a fun midi controller.

lol!

using this technology we should wire up octopus brains to drum machines, and dance to them funky mollusc beats.

Before reading Chaosmachine's post, my first thought was "is this possible to listen to music if one's mind is read by a machine?"

Wow, already? I'm not being sarcastic, I didn't expect this to be a reality in a long time.

freaking cool. Pretty unbelievable stuff...the future is amazing.

My first thought was stephen hawking, no more eye blinking to text \o/

okay i'm actually getting pretty scared

you'd have to be careful what you think!

  On 12/26/2009 at 8:19 PM, vasio said:

My first thought was stephen hawking, no more eye blinking to text \o/

if we hooked stephen hawking up to this thing, we would only discover that he spends about 2% of his day thinking about physics, and ~98% thinking about hardstyle mouth-fucking

it managed three vowel sounds.

useful.

uuu...aaaa....uuueee....ee...aaaa...

2010

so would this help determine if people who are in comas are really "there", but unable to communicate, or if they are truly brain dead? might be useful to know this if you are about to pull the plug on someone.

wait, wait, read the article dudes

  Quote

... in the current study, only three vowel sounds were tested ...

There at an early stage, they can only discern three different vowel sounds.

They do seem to have cracked part of the neural code though:

  Quote

“The study supported our hypothesis (based on the DIVA model, our neural network model of speech) that the premotor cortex represents intended speech as an ‘auditory trajectory,’ that is, as a set of key frequencies (formant frequencies) that vary with time in the acoustic signal we hear as speech,” Guenther said. “In other words, we could predict the intended sound directly from neural activity in the premotor cortex, rather than try to predict the positions of all the speech articulators individually and then try to reconstruct the intended sound (a much more difficult problem given the small number of neurons from which we recorded). This result provides our first insight into how neurons in the brain represent speech, something that has not been investigated before since there is no animal model for speech.”

So they are saying that the speech intention in the patients brain carries a sort of frequency information that can be used to map to certain speech sounds - thats interesting.

Also, the system apparently took 3 years to integrate itself with the brain:

  Quote

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.

Voiceless fricatives are allophonically voiced intervocalically