MHANet: Multi-scale Hybrid Attention Network for Auditory Attention Detection

TL;DR

This paper introduces MHANet, a novel multi-scale hybrid attention network that effectively captures multi-scale spatiotemporal dependencies in EEG signals for improved auditory attention detection, outperforming existing methods with fewer parameters.

Contribution

The paper proposes a multi-scale hybrid attention mechanism combined with spatiotemporal convolutions, enhancing EEG feature extraction for auditory attention detection.

Findings

Achieves state-of-the-art performance on three datasets.

Uses three times fewer trainable parameters than previous models.

Effectively captures long-short range spatiotemporal dependencies.

Abstract

Auditory attention detection (AAD) aims to detect the target speaker in a multi-talker environment from brain signals, such as electroencephalography (EEG), which has made great progress. However, most AAD methods solely utilize attention mechanisms sequentially and overlook valuable multi-scale contextual information within EEG signals, limiting their ability to capture long-short range spatiotemporal dependencies simultaneously. To address these issues, this paper proposes a multi-scale hybrid attention network (MHANet) for AAD, which consists of the multi-scale hybrid attention (MHA) module and the spatiotemporal convolution (STC) module. Specifically, MHA combines channel attention and multi-scale temporal and global attention mechanisms. This effectively extracts multi-scale temporal patterns within EEG signals and captures long-short range spatiotemporal dependencies simultaneously. To further improve the performance of AAD, STC utilizes temporal and spatial convolutions to aggregate expressive spatiotemporal representations. Experimental results show that the proposed MHANet achieves state-of-the-art performance with fewer trainable parameters across three datasets, 3 times lower than that of the most advanced model. Code is available at: https://github.com/fchest/MHANet.