TAnet: A New Temporal Attention Network for EEG-based Auditory Spatial Attention Decoding with a Short Decision Window

TL;DR

TAnet is a novel temporal attention network that significantly improves EEG-based auditory spatial attention decoding accuracy with decision windows shorter than one second, advancing real-time auditory attention detection.

Contribution

Introduces TAnet, an end-to-end multi-head attention model that enhances short-window EEG decoding performance over existing CNN-based and recent methods.

Findings

Achieved over 92% accuracy with 0.1 s window

Outperformed CNN-based methods in decoding accuracy

Potential applications in EEG-controlled hearing aids

Abstract

Auditory spatial attention detection (ASAD) is used to determine the direction of a listener's attention to a speaker by analyzing her/his electroencephalographic (EEG) signals. This study aimed to further improve the performance of ASAD with a short decision window (i.e., <1 s) rather than with long decision windows ranging from 1 to 5 seconds in previous studies. An end-to-end temporal attention network (i.e., TAnet) was introduced in this work. TAnet employs a multi-head attention (MHA) mechanism, which can more effectively capture the interactions among time steps in collected EEG signals and efficiently assign corresponding weights to those EEG time steps. Experiments demonstrated that, compared with the CNN-based method and recent ASAD methods, TAnet provided improved decoding performance in the KUL dataset, with decoding accuracies of 92.4% (decision window 0.1 s), 94.9% (0.25 s), 95.1% (0.3 s), 95.4% (0.4 s), and 95.5% (0.5 s) with short decision windows (i.e., <1 s). As a new ASAD model with a short decision window, TAnet can potentially facilitate the design of EEG-controlled intelligent hearing aids and sound recognition systems.