Speech synthesis from neural decoding of spoken sentences

Abstract

Technology that translates neural activity into speech would be transformative for people unable to communicate as a result of neurological impairment. Decoding speech from neural activity is challenging because speaking requires such precise and rapid multi-dimensional control of vocal tract articulators. Here, we designed a neural decoder that explicitly leverages kinematic and sound representations encoded in human cortical activity to synthesize audible speech. Recurrent neural networks first decoded directly recorded cortical activity into articulatory movement representations, and then transformed those representations into speech acoustics. In closed vocabulary tests, listeners could readily identify and transcribe neurally synthesized speech. Intermediate articulatory dynamics enhanced performance even with limited data. Decoded articulatory representations were highly conserved across speakers, enabling a component of the decoder be transferrable across participants. Furthermore, the decoder could synthesize speech when a participant silently mimed sentences. These findings advance the clinical viability of speech neuroprosthetic technology to restore spoken communication.