According to findings published in Scientific Reports, the technology called ‘vocoder’ is said to be able to construct or reconstruct words with “unprecedented clarity” by monitoring brain signals.
Vocoders are a category of voice codecs that analyse the human voice for audio data compression by being trained on recordings of real speech.
“Losing the power of one’s voice due to injury or disease is so devastating. With today’s study, we have a potential way to restore that power,” said Nima Mesgarani, the lead researcher.
“We’ve shown that, with the right technology, these people’s thoughts could be decoded and understood by any listener.”
The vocoder harnesses the power of speech synthesis and artificial intelligence while laying the groundwork for helping people with speech defects.
With previous researches showing that telltale patterns of activity appear in the brain when people speak, listen or imagine doing either, it synthesises speech after being trained on the nature of human voice.
Following series of tests with patients who couldn’t speak, Mesgarani said “the vocoder…represented the sounds the patients had originally listened to with surprising accuracy.
“In this scenario, if the wearer thinks ‘I need a glass of water,’ our system could take the brain signals generated by that thought, and turn them into synthesized, verbal speech.
“This would give anyone who has lost their ability to speak, whether through injury or disease, the renewed chance to connect to the world around them.”