Severely paralyzed man communicates using brain signals sent to his vocal tract

A severely paralyzed man was able to communicate using a new type of technology that translates signals from his brain to his vocal tract directly into words that appear on a screen. Developed by researchers at UC San Francisco, the technique is a more natural way for people with speech impairments to communicate than the other methods we’ve seen to date.

Until now, neuroprosthetic technology has only allowed crippled users to type only one letter at a time, a process that can be slow and laborious. He also tapped into parts of the brain that control the arm or hand, a system that is not necessarily intuitive to the subject.

The USCF system, however, uses an implant that is placed directly on the part of the brain dedicated to speaking. This way, the subject can mentally activate the brain patterns that they would normally use to say a word, and the system can translate the entire word, rather than single letters, on the screen.

To make this work, patients with normal speech volunteered to have their brain recordings analyzed for speech-related activities. The researchers were then able to analyze these models and develop new methods to decode them in real time, using statistical language models to improve accuracy.

However, the team was still unsure whether the brain signals controlling the vocal tract would still be intact in patients who had been paralyzed for many years. To this end, they recruited an anonymous participant (known as Bravo1) who worked with researchers to create a 50-word vocabulary that the team could decipher using advanced computer algorithms. This included words like “water”, “family” and “good” enough to allow the patient to create hundreds of sentences applicable to their daily life. The team also used an “auto-correct” feature similar to those found on consumer speech recognition apps.

To test the system, the team asked patient Bravo1 to answer questions such as “How are you today?” And “Do you want some water?” The patient’s speech attempt then appeared on the screen as “I’m fine” and “No, I’m not thirsty”.

The system was able to decode their speech at up to 18 wpm with 93% accuracy, with a median accuracy of 75%. It might not sound great compared to the 200 wpm possible with normal speech, but it’s way better than the speeds seen on previous neuroprosthetic systems.

“To our knowledge, this is the first successful demonstration of direct decoding of complete words from the brain activity of a person who is paralyzed and unable to speak,” said Edward Chang, MD, president of neurological surgery at UCSF and lead author of the study. “This has great promise for restoring communication by harnessing the brain’s natural speech machinery. “

The team said the trial represents proof of principle for this new type of “speech neuroprosthesis.” Then, they plan to expand the trial to include more participants, while also working to increase the number of words in the vocabulary and improve the rate of speech.