Voice Activity Detection in presence of background noise using EEG
This work addresses VAD for speech processing applications in noisy settings, but it is incremental as it builds on existing methods by adding EEG features.
The paper tackles voice activity detection (VAD) in noisy environments by combining acoustic and EEG features, showing that EEG-only VAD outperforms acoustic-only in noise, with results validated on two datasets under different noise conditions.
In this paper we demonstrate that performance of voice activity detection (VAD) system operating in presence of background noise can be improved by concatenating acoustic input features with electroencephalography (EEG) features. We also demonstrate that VAD using only EEG features shows better performance than VAD using only acoustic features in presence of background noise. We implemented a recurrent neural network (RNN) based VAD system and we demonstrate our results for two different data sets recorded in presence of different noise conditions in this paper. We finally demonstrate the ability to predict whether a person wish to continue speaking a sentence or not from EEG features.