학술논문
Advancing Speech Recognition With No Speech Or With Noisy Speech
Document Type
Conference
Author
Source
2019 27th European Signal Processing Conference (EUSIPCO) Signal Processing Conference (EUSIPCO), 2019 27th European. :1-5 Sep, 2019
Subject
Language
ISSN
2076-1465
Abstract
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.