Perhaps the two most famous speechless individuals are physicist Stephen Hawking and the late Robert Ebert, a film critic. To communicate with other individuals, both men used computers that generated synthesized voices, which sounded tinny, stilted and unnatural.
Now new technology could give speechless people a natural voice as unique to them as voices are to people who can speak.
“Right now, people who need to use synthesized voices to talk for them use a handful of generic voices, because creating them is time-consuming and costly,” said Rupal Patel, Ph.D, associate professor at Northeastern University. “We feel strongly the voice from the device should reflect something about that individual.”
With that philosophy, Patel, along with her research and development partner Tim Bunnell, Ph.D., a professor at the University of Delaware, developed VocaliD, a product that blends real human voices from healthy talkers with characteristics of the client’s unique speech patterns. The technique, called voice morphing, enables Patel and Bunnell to create a voice that is unique to the individual, and no longer has the now-traditional computerized sound.
The technology has positive implications for individuals who are autistic, or who suffer from disorders such as ALS or stroke, Patel said.
“There’s a relatively broad market of two-and-a-half to three million people who use devices to talk for them,” said Patel. “We’d love to see this technology being available to that population. We feel that if we can personalize the device, they will be more likely to use it and more socially acceptable.”
The technology is based on the fact that even speechless individuals can still make sounds, Bunnell said.