New Stanford tech enables typing directly from brain signals

How many monkeys does it take to type a passage of
Shakespeare? One monkey, equipped with brain-sensing technology.

Developed by scientists at Stanford University, the
technology can directly read brain signals to drive a cursor moving over a
keyboard. In an experiment with monkeys, the primates were able to transcribe
passages from the Hamlet and The New York Times at a rate of 12 words
per minute. Earlier versions of the technology were successfully tested in
people with paralysis, but the typing was slow and imprecise.

The latest study tests improvements to the speed and
accuracy of the technology that interprets brain signals and drives the cursor. 


fellow in Standford’s Department of Neurosurgery, Paul Nuyujukian and his colleagues developed the brain-sensing technology. Image source: Stanford University.

“Our results demonstrate that this interface may have great
promise for use in people,” said postdoctoral fellow in Standford’s Department
of Neurosurgery, Paul Nuyujukian. “It enables a typing rate sufficient for a
meaningful conversation.”

Alternative approaches for helping people with movement
disorders include track eye movements, or in the case of Stephen Hawking,
tracking movements of individual muscles in the face. Though helpful, these
options come with limitation, often requiring a degree of muscle control that
might be difficult for some people. Directly reading brain signals could
overcome some of these challenges and provide a way for people to communicate
their thoughts and emotions.

The Stanford team’s technology involves a multi-electrode
array implanted in the brain to directly read signals from a region that
typically directs hand and arm movements used to move a computer mouse. It’s
the algorithms used for translating the signals and making better letter
selections that the scientists have been improving upon.

“The interface we tested is exactly what a human would use,”
Nuyujukian said. “What we had never quantified before was the typing rate that
could be achieved.” Using the high-performing algorithms developed by
Nuyujukian and his colleagues, the animals could type more than three times
faster compared to earlier approaches.

According to the researchers, people using this system would
likely type slow while thinking about how to spell words or what they wish to
communicate. Despite that, Nuyujukian said even a rate lower than the 12 words
per minute achieved by monkeys would be a significant advance for people who
aren’t otherwise able to communicate effectively.

“Understand that we’re not using auto-completion here like your
smartphone does where it guesses your words for you,” Nuyujukian said.
Eventually the technology could be paired with the technology used by
smartphones or tablets to improve typing speeds.

The results of the study were published in IEE.