Columbia University team constructed clear synthetic speech by processing human brain activity.
Researchers in the US have for the first time constructed clear and intelligible synthetic speech using computer processing of human brain activity, in a significant step towards creating technology that can read people’s thoughts.
The technology would give an artificial voice to people deprived of speech through disease or injury by reading their thoughts rather that relying on input from a keyboard or facial movements.
“Losing the power of one’s voice . . . is devastating,” said Nima Mesgarani, project leader at Columbia University in New York. “With today’s study, we have a potential way to restore that power. We’ve shown that, with the right technology, these people’s thoughts could be decoded and understood by any listener.”