Physi­cist Stephen Hawking has long dealt with a degen­er­a­tive dis­ease that leaves him unable to speak. Instead, he uses a speech syn­the­sizer that bel­lows out his words in a now-​​recognizable robotic male voice. It works for Hawking–he’s an adult male. But sim­ilar robotic voices are used for little girls and all the other 2.5 mil­lion Amer­i­cans unable to talk. These people would speak in dra­mat­i­cally dif­ferent vocal reg­is­ters if they had the ability.

At this month’s TED­Women event in San Fran­cisco, speech sci­en­tist Rupal Patel unveiledVocaliD, a project that will create pros­thetic voices that actu­ally sound like the people who use them. It could be a life-​​changing devel­op­ment in the robo-​​voice world.

To create a pros­thetic voice, Patel and her team at North­eastern Uni­ver­sity gather as many acoustical prop­er­ties as they can from the person being fitted with the voice (that is, all the sound they’re still able to pro­duce) and overlay those prop­er­ties on a voice from a sur­ro­gate voice donor who is the same gender, size, and age. A voice donor typ­i­cally spends three to four hours reciting phrases that cover all the com­bi­na­tions of sound present in a language.

Read the article at Fast Company →