Scientists at the University of California have announced a breakthrough technology to read your thoughts!

Once thought (pardon the pun) to be a thing of science fiction, the new device is capable of reading your mind and speaking your thoughts.

The device is aimed at the medical field, as a way to bring speech back to those who’ve lost the ability to talk.  There are a number of diseases which can lead to speech loss, that could benefit from this new technology; Parkinson’s Disease, Multiple Sclerosis, Motor Neurone Disease, Brain Injuries, Throat Cancer.

The idea isn’t new – it’s been tried before without much success, but what’s different this time is how the scientists are looking at the brain to figure out what you’re trying to say.

Previously, scientists have tried to analyse the brain to spot patterns in the electrical signals that relate to specific words.   This is a huge undertaking as you have to closely study the brain to learn each individual word.

Instead, the new approach looks at how the brain controls the shape of the mouth when talking.   The technology watches this specific area of the brain and tries to predict what sound would be produced.   By then simulating the sound, the device “speaks” on behalf of the patient based on their brain signals.

It’s not perfect but it’s getting close!   In a test, listeners were able to understand 70% of the words generated.  Josh Chartier, one of the scientists working on the technology said

“We’re quite good at synthesizing slower speech sounds like ‘sh’ and ‘z’ as well as maintaining the rhythms and intonations of speech and the speaker’s gender and identity, but some of the more abrupt sounds like ‘b’s and ‘p’s get a bit fuzzy. Still, the levels of accuracy we produced here would be an amazing improvement in real-time communication compared to what’s currently available.”

You can hear a sample of the synthesized speech here:

It’s pretty amazing to wonder where this technology will be in a few years’ time, and what it will be capable of given this advanced early sample!

Edward Chang, a professor of neurological surgery, who is leading the development said “For the first time, this study demonstrates that we can generate entire spoken sentences based on an individual’s brain activity.  This is an exhilarating proof of principle that with technology that is already within reach, we should be able to build a device that is clinically viable in patients with speech loss.”

For more information about the research, check out the following link: