For years, Pancho communicated by spelling words on a computer using a pointer attached to a baseball cap, an arduous method that allowed him to write about five correct words per minute.
“I had to tilt / tilt my head forward, down and press a key letter one by one to type,” he wrote via email.
Last year, researchers gave him another device that involved a head-controlled mouse, but it is still not as fast as brain electrodes in research sessions.
Through the electrodes, Pancho communicated 15 to 18 words per minute. That was the maximum speed the study allowed because the computer waited between prompts. Dr. Chang says faster decoding is possible, although it’s unclear if it will come close to the rate of typical conversational speech – around 150 words per minute. Speed is a key reason the project focuses on speaking, directly tapping into the brain’s word production system rather than the hand movements involved in writing or writing.
“It’s the most natural way for people to communicate,” he said.
Pancho’s upbeat personality has helped researchers overcome challenges, but it also makes speech recognition uneven at times.
“Sometimes I can’t control my emotions and laugh a lot and the experiment is not going very well,” she wrote by email.
Dr. Chang recalled times when, after the algorithm successfully identified a sentence, “he could be seen visibly shaking and looked like he was laughing.” When that happened or when, during repetitive tasks, he yawned or became distracted, “it didn’t work very well because I wasn’t really focused on understanding those words. So we have some things to work on because obviously we want it to work all the time. “
The algorithm sometimes confused words with similar phonetic sounds, identifying “go” as “bring”, “do” as “you” and words beginning with “F” – “faith”, “family”, “feel” – as a V -word, “very.”
