New brain-computer interface transmits thoughts to speech in record time
Breakthrough is major step towards real-time speech conversion
Your support helps us to tell the story
From reproductive rights to climate change to Big Tech, The Independent is on the ground when the story is developing. Whether it's investigating the financials of Elon Musk's pro-Trump PAC or producing our latest documentary, 'The A Word', which shines a light on the American women fighting for reproductive rights, we know how important it is to parse out the facts from the messaging.
At such a critical moment in US history, we need reporters on the ground. Your donation allows us to keep sending journalists to speak to both sides of the story.
The Independent is trusted by Americans across the entire political spectrum. And unlike many other quality news outlets, we choose not to lock Americans out of our reporting and analysis with paywalls. We believe quality journalism should be available to everyone, paid for by those who can afford it.
Your support makes all the difference.A new brain-computer interface (BCI) has set a new record for translating thoughts to speech, neuroscientists have claimed.
A team from Stanford University said the brain chip is capable of decoding up to 62 words per minute, allowing people to communicate at speeds close to natural conversation.
Researchers fitted the device to a non-verbal patient with amyotrophic lateral sclerosis (ALS), allowing them to produce more than a word a second with a pre-programmed vocabulary of 125,000 words.
“Our BCI decoded speech at 62 words per minute, which is 3.4 times faster than the prior record for any kind of BCI and begins to approach the speed of natural conversation (160 words per minute),” the researchers wrote in a preprint paper titled ‘A high-performance speech neuroprosthesis’.
“These results show a feasible path forward for using intracortical speech BCIs to restore rapid communication to people with paralysis who can no longer speak.”
The BCI system worked by analysing minor facial movements as the ALS patient attempted to form words with their mouth, and then decoding the associated neural activity into words.
The Stanford scientists said it marks the first time that a BCI has also far exceeded the speed of other technologies currently used by people who can no longer speak, such as eye-tracking or keyboard based approaches.
Despite the success of the experiments, the BCI system still needs to be improved before it is seen as a viable replacement for current methods.
With an error rate of around 20 per cent, the researchers wrote in the paper that “it is not yet a complete, clinically viable system”.
It is one of numerous efforts by universities and startups to develop BCI devices, which include Science Corp and Elon Musk’s Neuralink.
Mr Musk said during an event last year that Neuralink plans to begin the first human trials of its device in 2023, having already tested it on pigs and monkeys. The tech billionaire claims the brain chip will go far beyond returning speech to non-verbal patients, offering “full-bandwidth data streaming” to the brain.
Join our commenting forum
Join thought-provoking conversations, follow other Independent readers and see their replies
Comments