From Brain Signals to Sentences
A significant breakthrough has struck the scientific community! Researchers in California successfully transposed the brain signals of a man suffering from an inability to speak. In other words, they were able to convert his raw thoughts into written sentences. According to neurosurgeon Edward Chang, the senior author of the study, this is the first known “successful demonstration of [the] direct decoding of full words from the brain activity of someone who is paralyzed and cannot speak.”
The study, known as “BRAVO” (Brain Computer Interface Restoration of Arm and Voice), was performed on a man in his late 30s that was paralyzed due to a brainstem stroke over 15 years ago. He had very limited mobility in his head, neck, and limbs. He communicated prior by a pointer attached to a baseball cap that would be used to poke letters on a screen.
Dr. Chang and his research associates implanted electrodes into the speech control center–the cerebrum–of the aforementioned subject’s brain. They worked with the man to create a 50-word vocabulary bank with words like “water,” “family,” and “good,” which Chang and his team were able to pair with brain activity patterns through advanced computer algorithms. To test this approach, the researchers had the volunteer repeat sentences created from words in his vocabulary bank, and they would record the subsequent neural activity. He was then asked short questions such as “How are you today?” and “Would you like some water?” After hearing the questions, the man responded via computer screen: “I am very good” and “No, I am not thirsty.”
Translating the Mind
How was this incredible feat possible, you ask? The researchers translated using brain signals that were intended to control muscles of the vocal system for speaking, rather than the signals to move the arm or hand for typing. This approach, known as speech neuroprosthesis, taps into the fluid aspects of speech, which promises more rapid and natural communication for the speech impaired.
By successfully intercepting and translating brain signals associated with speech-related muscles, the team determined that their implanted electrode system could decode words from the subject’s neural activity at a rate of up to 18 words per minute with up to 93% accuracy. Similar to what is used in commercial speech recognition software, an “auto-correct” function is attributed to the success of the technology.
Chang and his team are currently working on increasing the vocabulary and rate of speech of their technology, as well as expanding the trial to include more test subjects with paralysis and communication deficiencies. With hard work and time, their efforts could contribute to the full restoration of speech for millions upon millions of people.
Life Insurance Questions?
We hope that this information on communicating through translated brain signals was useful to you!
If you’d like to learn how we can help you plan your retirement, call Empower Brokerage at (888) 539-1633 to speak to one of our Life and Annuity experts or leave a comment down below.
See our other websites: