Advancing Speech Recognition With No Speech Or With Noisy Speech

2019/06/17 by Krishna, Gautam, Tran, Co, Carnahan, Mason +1
#Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.1906.08871

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.

Related

• Speech Recognition with no speech or with noisy speech
• Improving EEG based Continuous Speech Recognition
• Continuous Speech Recognition using EEG and Video
• Continuous Silent Speech Recognition using EEG
• Speech Recognition With No Speech Or With Noisy Speech Beyond English