The Neuralynx System translates thoughts into speech. It connects to the neurons, transmitting signals wirelessly to a laptop, which translates the brain activity to spoken English. It's not science fiction: They tried it with a paralysed 26-year-old and it works.
According to the research results, they inserted the electrodes into the patient's brain, installing signal amplifiers and transmitters under the scalp. The circuitry - powered by an induction power supply - transmitted the signals to a laptop via FM radio. The software then converts the analogue signal to digital data that the neural decoder interprets into speech commands, which are then sent to the synthesiser.
The whole process takes 50 milliseconds, which is the same amount it takes any normal person to do the same process using their vocal chords and mouth. According to Neuralynx project leader Frank Guenther - from the Department of Cognitive and Neural Systems and the Sargent College of Health and Rehabilitation Sciences at Boston University - the system is going to get even better soon.
The results of our study show that a brain-machine interface (BMI) user can control sound output directly, rather than having to use a (relatively slow) typing process. Our immediate plans involve the implementation of a new synthesiser that can produce consonants as well as vowels but remains simple enough for a BMI user to control. We are also working on hardware that will greatly increase the number of neurons that are recorded. We expect to tap into at least 10 times as many neurons in the next implant recipient, which should lead to a dramatic improvement in performance.
Obviously, this is going to be a miraculous thing for people who can't talk because of nerve damage, or any other reason. It could also mean the beginning of something bigger, enabling different kinds of communication. Imagine an implant that could do the same thing on reverse, basically enabling long distance telepathy.
Hmmm... on second thought, this could be the best worst idea ever created. [Physorg]