Continuous Silent Speech Recognition using EEG

TL;DR

This study demonstrates the feasibility of continuous silent speech recognition using EEG signals by implementing a CTC-based ASR model to translate brain signals into text without vocalization.

Contribution

The paper introduces a novel approach for silent speech recognition using EEG and a CTC model, achieving initial proof of concept for this technology.

Findings

EEG signals can be used for silent speech recognition

A CTC-based model effectively translates EEG to text

Successful recognition of 30 English sentences

Abstract

In this paper we explore continuous silent speech recognition using electroencephalography (EEG) signals. We implemented a connectionist temporal classification (CTC) automatic speech recognition (ASR) model to translate EEG signals recorded in parallel while subjects were reading English sentences in their mind without producing any voice to text. Our results demonstrate the feasibility of using EEG signals for performing continuous silent speech recognition. We demonstrate our results for a limited English vocabulary consisting of 30 unique sentences.