Stephen Hawking’s voice is one of the most instantly recognisable in the world. But millions of people with severe speech impairments who rely on computerised voices, lose their vocal identity as there are only a few voice options available. But a now one organisation is encouraging people to donate their voices so that it can create voices as ‘unique as fingerprints’ to suit individuals who are losing their own. While VocaliD is still in its early stages and experts are perfecting the recording process, they hope to use a web program or phone app so that people can record their voice remotely in a quiet place, as the better the recording, the more realistic the voice created. To build the custom voices, experts at VocaliD – whose founders are based in Delaware and Boston – extract whatever sounds a speech-impaired person can produce and apply them to a synthetic voice that is partially created from a surrogate voice donor. Donor voices are selected to match a ‘target talker’ in age, size and sex so that their new synthetic voice contains as much of their original vocal identity as possible – but with the speech clarity of the surrogate voice donor. ‘It’s a simple idea that could make a powerful impact on the lives of those who rely on synthetic voices to express themselves, the organisation said.
VocaliD estimates that there are tens of millions of people across the world who rely on computerised voices to communicate and two-and-a-half million in the U.S. alone. The few options available often lack personality and sound like a computer. Every person has a unique ‘vocal source’, which is a buzzing created by the larynx or voice box, that reflects their anatomy. The source is pushed through the rest of the vocal tract – the chambers in the head and neck – which change shapes to produce consonants and vowels.