Here’s a good deed you can do without parting with a single thing. Synthetic voices for people who have lost the ability to speak only come in generic types — think of Stephen Hawking’s voice — but one fascinating project wants to build custom voices for each person. To do that they need your help: specifically, a recording of your voice.
VocalID is the brainchild of two speech scientists, who are turning their research into a much larger project. Voice is intensely personal and, like a prosthetic leg or arm, it makes sense it should be customised to each person.
Here’s how it works — and don’t worry, this does not mean someone will be walking around with the same voice as you out there:
After recording a couple hours of audio in, say, a quiet room with an iPhone, you send it to VocalID, where a program called ModelTalker chops it up into the basic units of speech that can be recombined as novel words and sentences. In that same step, characteristics of the patient’s voice — based on what limited sounds they can make — are blended in to the donor’s to create a whole new one. You can listen to how it works out on VocalID’s website.
VocalID is still in its beginning stages, and they’re looking for help from everyone including voice donors, financial support, and programmers. A priority is making voice donation even easier, cutting down recording time, especially for kids. But as it stands already, your voice is just about the easiest thing to donate. [New Scientist]
Top image: Sergey Nevins/Shutterstock