San Francisco – How do you translate thoughts into spoken words? A team of scientists from the University of California have discovered a new piece of that puzzle, and the result is a surprising convincing pattern of synthetic speech.
The scientists created a system that translates brain waves into words by focusing on physical movements related to speech, rather than the sound of words trying to be communicated. They found looking for the tongue, larynx and other speech mechanisms allowed to reproduce voice sounds in a more reliable way than, say, trying to match brain waves to predicted speech sounds.
Using this information, the team created and computer program that simulates the movements of vocal tract by honing in the brain's speech centers.
Take a look at this type of speech modeling. You can see the connection between the intended words, and the way those words are formed by different parts of the vocal tract.
The team's findings were recently published in the journal Nature. The paper is a new method of life-changing technology for people with severe speech disorders, or other conditions that limit their ability to communicate.
"It's been a longstanding goal of our lab to create technologies to restore communication for patients with severe speech disability," Edward Chang, one of the project's co-authors, said in a press briefing. "We want to create technologies that can reproduce speech directly from human brain activity. This study provides proof of the principle that this is possible."
That's not the only exciting takeaway from the team's research. According to Chang, their mechanical speech process was actually applied from one person to another.
"The neural code for vocal movements is shared across different individuals, and that artificial vocal tract modeled on one person's voice" Chang explains. "This is a speech decoder that trained in one person with intact speech."
According to another recent study cited by the UC scientists, communication technologies for people with speech and motor limitations are evolving, but can still be frustrating and inaccurate. If this latest breakthrough can eventually be applied to an individual patient level, it could open up and new world of understanding, and being understood.