A lightweight VAD model with a learnable sinc filterbank and a squared-margin ranking loss reports higher AUROC and F2 scores on AVA-Speech and ACAM using only 8.0k parameters.
Voice Activity Detection in presence of background noise using EEG
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SincQDR-VAD: A Noise-Robust Voice Activity Detection Framework Leveraging Learnable Filters and Ranking-Aware Optimization
A lightweight VAD model with a learnable sinc filterbank and a squared-margin ranking loss reports higher AUROC and F2 scores on AVA-Speech and ACAM using only 8.0k parameters.