Continuous Silent Speech Recognition using EEG
This addresses the problem of enabling communication for individuals with speech impairments, but it is incremental as it builds on existing EEG and ASR methods with a small-scale demonstration.
The paper tackled continuous silent speech recognition by translating EEG signals from subjects silently reading English sentences into text using a CTC-based ASR model, achieving feasibility with results on a limited vocabulary of 30 unique sentences.
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.