Medindia LOGIN REGISTER
Medindia

Speech Synthesiser Helps Paralysed Patient to Produce Sounds at the Speed of His Thought

by Hannah Punitha on Nov 24 2008 5:12 PM

A paralysed man who can neither move nor communicate has been enabled to use a speech synthesizer to produce vowel sounds as he thinks them, with the aid of an electrode implanted into his brain.

The researchers behind the breakthrough work say that it has raised hopes that one day similar patients will be enabled to produce whole sentences using signals from their brains.

Frank Guenther, of Boston University in Massachusetts, revealed that his team first had to determine whether the man's brain could produce the same speech signals as a healthy person's, and thus they scanned his brain using functional magnetic resonance imaging (fMRI) while he attempted to say certain vowels.

Having determined that the signals were the same, the researchers implanted an electrode - designed by neuroscientist Philip Kennedy of the firm Neural Signals in Duluth, Georgia - into the speech-production areas of the subject's brain.

The electrode, which will remain there for the foreseeable future, is different to others used for brain-computer interfaces, most of which are fixed to the skull rather than within a specific part of the brain.

The electrode used by the researchers is impregnated with neurotrophic factors, which encourage neurons to grow into and around the electrode, anchoring it in place and allowing it to be recorded from for a much longer time.

Guenther revealed that after implanting the electrode, his group used a computer model of speech that Guenther had developed over the past 15 years to decode the signals coming from the subject's brain, and discern which vowel sounds he was thinking about.

Advertisement
While presenting the results of the study at the Society for Neuroscience meeting in Washington DC, Guenther revealed that the patients had thus far been able "to produce three vowel sounds with good accuracy," and that that happened as quickly as normal speech.

"The long-term goal within five years is to have him use the speech brain-computer interface to produce words directly," he said.

Advertisement
Guenther claims that this is the first brain-computer interface that has been tailored for speech.

His team consider themselves to be privileged to be involved in the project.

"This was the first application where we see an individual improve his abilities based on something we theorized years ago," he says.

The researchers have revealed that their next step is to train their computer decoder to recognize consonants so that patients can form whole words, and even sentences.

They hope that with developments in technology, they can implant more electrodes in their next patient to transmit a more detailed signal.

Source-ANI
SPH


Advertisement