Speech Recognition with no speech or with noisy speech

TL;DR

This paper explores using EEG signals to improve speech recognition in noisy environments and demonstrates high-accuracy word recognition from EEG alone, offering a novel approach to robust ASR.

Contribution

It introduces EEG-based features and distillation training methods to enhance ASR performance amidst noise and enables word recognition solely from EEG signals.

Findings

EEG features improve ASR accuracy in noisy conditions

Distillation training enhances speech recognition performance

High-accuracy word recognition from EEG without speech signals

Abstract

The performance of automatic speech recognition systems(ASR) degrades in the presence of noisy speech. This paper demonstrates that using electroencephalography (EEG) can help automatic speech recognition systems overcome performance loss in the presence of noise. The paper also shows that distillation training of automatic speech recognition systems using EEG features will increase their performance. Finally, we demonstrate the ability to recognize words from EEG with no speech signal on a limited English vocabulary with high accuracy.