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.
翻译:在本文中,我们展示了结束持续语音识别(CSR)的终结,即使用没有语音信号的电脑摄影信号结束连续语音识别(EEEG)作为输入;为进行识别,实施了基于自动语音识别(ASR)和连接器时间分类(CTC)的自动语音识别(ASR)和连接器时间分类(CTC)系统等关注模型;我们通过与 EEG 功能引信,进一步展示了噪音语音识别(CSR)。