Recognition Of Silently Spoken Word From Eeg Signals Using Dense Attention Network (DAN)

Sahil Datta; Akuha Aondoakaa; Jorunn Jo Holmberg; Elena Antonova

ICASSP 2022accepted0 citations

Recognition Of Silently Spoken Word From Eeg Signals Using Dense Attention Network (DAN)

Sahil Datta, Akuha Aondoakaa, Jorunn Jo Holmberg, Elena Antonova

Abstract

In this paper, we propose a method for recognizing silently spoken words from electroencephalogram (EEG) signals using a Dense Attention Network (DAN). The proposed network learns features from the EEG data by applying the self-attention mechanism on temporal, spectral, and spatial (electrodes) dimensions. We examined the effectiveness of the proposed network in extracting spatio-spectro-temporal in-formation from EEG signals and provide a network for recognition of silently spoken words. The DAN achieved a recognition rate of 80.7% in leave-trials-out (LTO) and 75.1% in leave-subject-out (LSO) cross validation methods. In a direct comparison with other methods, the DAN outperformed other existing techniques in recognition of silently spoken words.

BibTeX

@inproceedings{icassp2022_recognitionofsil,
  title = {Recognition Of Silently Spoken Word From Eeg Signals Using Dense Attention Network (DAN)},
  author = {Sahil Datta and Akuha Aondoakaa and Jorunn Jo Holmberg and Elena Antonova},
  booktitle = {ICASSP 2022},
  year = {2022}
}