Two studies published in the journal Nature indicate progress in the race to teach computers to translate brain signals into text. The technology is attracting millions in investment, including Elon Musk’s brain-implant company, Neuralink Corp.
But it goes well beyond Musk and his concept of a world where non-disabled people merge with computers to enhance their intelligence and should also focus on the benefits of helping people who have lost their ability to communicate or move. For example, restoring the ability to speak to stroke victims or for those with a disease like ALS to help paralyzed people regain control over their muscles should be part of the goals.
In the Nature studies, researchers used different implants to collect electronic signals from volunteers’ brains and different algorithms to interpret them. Attempts at speech could be converted to text at a rate of 60-70 words per minute. While still half as fast as a typical person’s cadence, it’s a vast improvement over earlier brain-computer interfaces. The computer was able to decode speech with remarkable accuracy.
UCSF researchers developed a personalized avatar for their volunteer, paralyzed by a brainstem stroke more than 18 years ago. The avatar uses her own voice, taken from a clip of her speaking at her wedding, and integrates facial expressions.
The problem is that turning these technologies into profitable products will be very tough. The devices will be expensive and require specific expertise and training. Consider Second Sight Medical Products, a company that developed retinal implants. In 2020, the company began winding down operations before eventually merging with another firm, leaving people who relied on their bionic eyes in the lurch.
Musk has helped by stimulating interest and investment in the field. That should help get the hardware (the actual brain implant) to a point where regulators feel comfortable with its long-term safety.
