VocaliD aims to give a voice to those who cannot speak by customising the voice of people who can.Very soon, speech-impaired patients will not be stuck with just the generic computerised voices such as physicist Stephen Hawking in order to be heard by others. A research team, that includes an Indian-origin scientist at the periphery is currently working on an app that may allow people to donate their voice to those who have severe speech impediments owing to stroke, Parkinson’s or cerebral palsy etc.
The programme: VocaliD aims to give a voice to those who cannot speak by customising the voice of people who can into synthetic speech. “For these individuals, this is the only way that they interact with people around them,” Rupal Patel, a speech scientist at Northeastern University in Boston and VocaliD’s co—director was quoted as saying, referring to generic computerised voices currently available. However, all this is going to change soon.
Under VocaliD, the researchers first listen to the limited sounds that their patients are able to produce. This gives them an idea regarding the sound of the person’s speech: whether it’s high—pitched, raspy or breathy. A surrogate is then selected, who is similar in age and sex to the patient. This surrogate then donates his voice, by reading through thousand sample sentences, sourced from various books. His/her voice is then blended with the patient’s and broken down into tiny units that make up speech. This is achieved by a software tool called ModelTalker. “You probably wouldn’t recognise it as having come from the donor any more,” Timothy Bunnell of the University of Delaware in Wilmington, who created ModelTalker and is also VocaliD’s co—director was quoted as saying.
Accha
ReplyDelete