Towards Voice Reconstruction from EEG during Imagined Speech

TL;DR

This paper introduces NeuroTalk, a novel method for reconstructing a person's voice from non-invasive EEG signals during imagined speech, bridging the gap between brain activity and speech synthesis.

Contribution

The paper presents a new model that generalizes from spoken to imagined speech EEG, enabling voice reconstruction without invasive measures and incorporating phoneme decoding.

Findings

Successful voice reconstruction from imagined speech EEG.

Model generalizes from spoken to imagined speech.

Potential for speech synthesis from brain signals.

Abstract

Translating imagined speech from human brain activity into voice is a challenging and absorbing research issue that can provide new means of human communication via brain signals. Endeavors toward reconstructing speech from brain activity have shown their potential using invasive measures of spoken speech data, however, have faced challenges in reconstructing imagined speech. In this paper, we propose NeuroTalk, which converts non-invasive brain signals of imagined speech into the user's own voice. Our model was trained with spoken speech EEG which was generalized to adapt to the domain of imagined speech, thus allowing natural correspondence between the imagined speech and the voice as a ground truth. In our framework, automatic speech recognition decoder contributed to decomposing the phonemes of generated speech, thereby displaying the potential of voice reconstruction from unseen words. Our results imply the potential of speech synthesis from human EEG signals, not only from spoken speech but also from the brain signals of imagined speech.