In DepthNeuroscience

Computers turn neural signals into speech

See allHide authors and affiliations

Science  04 Jan 2019:
Vol. 363, Issue 6422, pp. 14
DOI: 10.1126/science.363.6422.14

You are currently viewing the summary.

View Full Text

Log in to view the full text

Log in through your institution

Log in through your institution


For many people who are paralyzed and unable to speak, signals of what they'd like to say hide in their brains. No one has been able to decipher those signals directly. But three research teams recently made progress in turning data from electrodes surgically placed on the brain into computer-generated speech. These teams haven't yet managed to re-create speech that people merely imagine. But by monitoring parts of the brain as participants either read aloud, silently mouthed speech, or listened to recordings, the researchers were able to use computational models called neural networks to reconstruct words and sentences that were close enough, in some cases, to be intelligible to human listeners.