Advancing Speech Recognition With No Speech Or With Noisy Speech
Gautam Krishna, Co Tran, Mason Carnahan, Ahmed H. Tewfik · 2019
In this paper we demonstrate end to end continuous speech recognition (CSR) using electroencephalography (EEG) signals with no speech signal as input. An attention model based automatic speech recognition (ASR) and connectionist temporal classification (CTC) based ASR systems were implemented for performing recognition. We further demonstrate CSR for noisy speech by fusing with EEG features.