Now you can donate your voice. Scientists want clips to develop personalized...

Now you can donate your voice. Scientists want clips to develop personalized tones for people unable to talk

0 408

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.

article-2591549-1CA5675700000578-909_634x466VocaliD 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.

 While some people cannot manipulate their vocal filter because they have a neuromotor speech impairment, many people have some sort of control of their vocal source. It is people with conditions such as Parkinson’s and cerebral palsy that VocaliD could help by building a customised synthetic voice based on a person’s vocal source and a donor’s speech. Experts use several thousand sentences recorded by a donor to make a new voice, in a similar way to how engineers created Siri and other voice recognition technologies. The recording process takes between two and three hours and donors read or repeat short sentences that together cover all the combinations of sounds that occur in the English language. Using the recording, experts then use software that blends the surrogate’s voice with the sounds of the ‘target talker’ or patient, which creates speech ‘units’ like vowel sounds and consonants. Once all these units have been made, the synthetic voice is created and allows patients to say any sentence – even those not pre-recorded by the surrogate. There is a chance that by being a donor, someone could have exactly the same voice as you, but the organisation said it is ‘unlikely’ as the new voice is a blend so will probably only have elements of  the donor’s voice.
published by Dailymail   other sources: smithsonianmag and newscientist