How to build a human voice
Smithsonian Magazine - 03/25/2014
One of the more recognizable voices in the world belongs to Stephen Hawking—although, of course, it is not actually the famous scientist’s voice at all, but one that’s computer-generated in response to his facial motions. He’s been using a synthesizer to speak for almost 25 years now, his voice and ability to move lost long ago to ALS, or Lou Gehrig’s disease. Today, the British astrophysicist is identified through his robotic monotone, one that actually has an American accent.
But the truth is, Hawking shares that computer-generated voice with thousands of other people, some young girls, some older women, and others of all ages and ethnicities across the world. All of them, unable to speak naturally, think of it as their own, though there’s nothing unique about it.
And that just doesn’t seem right to Rupal Patel.
Patel is a speech scientist and director of the the new Center for Speech Science and Technology at Northeastern University. She has long long felt that a voice helps define an individual; it clearly shapes how a person is known in the world. Even if people can’t speak, she says, shouldn’t they have an opportunity to communicate through voices that are truer to who they are?