Mindreading Software Can Decode Your Thoughts and Translate It Into Words

A mindreading software called Brain-to-Text can possibly decode your thoughts and translate them into words.

To come up with the technology, a team of scientists recorded and monitored the brain activities of seven individuals undergoing epilepsy surgery in 2011. The participants were then asked to read aloud and read in silence the text of the Gettysbury Address, Charmed fan fiction and the nursery rhyme Humpty Dumpty being flashed on the screen.

The team then utilized the spoken data to create a personal decoder for each patient which interpreted the data and transformed it into a visual representation. Afterwards, the decoder was then applied to brain activity during silent reading. The scientists found that several words that were being thought were reconstructed through neural imaging.

PHOTO CREDIT: The Daily Mail UK
PHOTO CREDIT: The Daily Mail UK

 Speaking to New Scientist, Brian Pasley said: “If you’re reading text in a newspaper or book, you hear a voice in your own head. We’re trying to decode the brain activity related to that voice to create a medical prosthesis that can allow someone who is paralysed or locked in to speak.”

But since each individual’s brain is unique and the brain waves transmitting phonetic data is so sensitive, the technology can’t be easily made commercially available since each brain must be assessed individually.

The promising computer program can possibly help stroke victims and people suffering from degenerative diseases whose ability to communicate had been affected.

Currently, the team of scientists are exploring the possibility of using the technology to patients suffering from Aphasia. This condition, which usually occurs after a person suffers from a head injury or stroke, affects an individual’s ability to express and understand both written and verbal language.

“This is just the beginning. The prospects of this are really endless,” said Peter Brunner, the co-author of the study.

Share this: