Advancing Speech Recognition With No Speech Or With Noisy Speech
arXiv:1906.08871v952 citations
Originality Synthesis-oriented
AI Analysis
This addresses speech recognition challenges in noisy or silent environments, but appears incremental.
The paper tackled continuous speech recognition using EEG signals without speech input and improved noisy speech recognition by fusing EEG features, achieving unspecified results.
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.