A Biologically Inspired Attention Network for EEG-Based Auditory Attention Detection
Peiwen Li, Siqi Cai, Enze Su, Longhan Xie
Abstract
Decoding auditory attention in a cocktail party from neural activities is crucial in the brain-computer interfaces (BCIs). Given that the speech-electroencephalography (EEG) relationships are informative about attentional focus, we propose a novel framework called the biologically inspired attention network (BIAnet) to capture the interactions between EEG and speech. With the neural attention mechanism, the BIAnet can model how each EEG frequency band is related to the subband envelopes of speech by dynamically assigning weights to individual frequency bands at run-time. Results show that the proposed BIAnet outperforms state-of-the-art AAD methods on two publicly available datasets. We also analyze how the BIAnet works and the frequency-specific interactions between EEG and speech signals through data visualization. Overall, the proposed BIAnet provides an accurate, low-latency, and interpretable AAD approach, which has the potential to be extended to general problems in BCIs.