You Can Now Donate Your Voice to People Who Can't Speak | Smart News | Smithsonian
Current Issue
September 2014  magazine cover
Subscribe

Save 81% off the newsstand price!

Keeping you current

voiceover (Mikka Skaffari)

You Can Now Donate Your Voice to People Who Can't Speak

You don’t have to be dead to donate a piece of yourself. A new company lets people donate their voices to those without them

smithsonian.com

The little D on your license indicates that you’re willing to donate your organs when you die. But you don’t have to be dead to donate a piece of yourself. A new company lets people donate their voices to those without them. 

VocaliD allows people to record themselves to contribute to a database of voices for those who have lost their voices to things like stroke, Parkinson’s or cerebral palsy. The premise is to gather up a database of human voices, and create a personalized synthetic voice out of those recordings. Aviva Rutkin at New Scientist explains:

A surrogate who is similar in age and the same sex is selected to donate their voice. That person reads through several thousand sample sentences, sourced from classic books like White Fang, The Wonderful Wizard of Ozand The Velveteen Rabbit.

Then, using a software tool called ModelTalker, the surrogate's voice is blended with the patient's and stripped down into the tiny units that make up speech. Even a single vowel sound might be broken into two or three parts that can then be assembled into new words. "You probably wouldn't recognise it as having come from the donor any more," says Timothy Bunnell of the University of Delaware in Wilmington, who created ModelTalker and is also VocaliD's co-director.*

Right now, it takes a long time to give your voice. Donors have to read at least 800 sentences to create a usable voice and 3,000 for a natural one. Rutkin did it, and she spent hours in a studio recording herself reading from books. But if people all over the world commit to donating, VocaliD could build a bank that will allow people with all kinds of accents and histories to find a voice that feels like their own. 

*We've heard from VocaliD that the New Scientist blockquote reproduced here does not make clear that it is "the VocaliD software not ModelTalker" that blends "the surrogate's voice with the patient's voice. ModelTalker is just the synthesis engine."

Tags
About Rose Eveleth
Rose Eveleth

Rose Eveleth is a writer for Smart News and a producer/designer/ science writer/ animator based in Brooklyn. Her work has appeared in the New York Times, Scientific American, Story Collider, TED-Ed and OnEarth.

Read more from this author |

Comment on this Story

comments powered by Disqus