用多尺度注意力捕捉脑电中远近时序依赖，提升听觉注意检测精度。
MHANet: Multi-scale Hybrid Attention Network for Auditory Attention Detection
- 融合通道注意力与多尺度时序全局注意力，捕捉多层次时间模式。
- 在三个数据集上性能领先，参数量仅为最先进模型的1/3。
- 适合脑机接口、语音分离等需要高精度听觉注意识别的研究者。
听觉注意检测（AAD）旨在从脑电信号（如EEG）中识别多人对话环境下的目标说话人，已有显著进展。然而，多数方法仅顺序使用注意力机制，忽略了EEG信号中的多尺度上下文信息，难以同时捕捉长短期时空依赖。为此，本文提出多尺度混合注意力网络（MHANet），包含多尺度混合注意力（MHA）模块和时空卷积（STC）模块。MHA结合通道注意力与多尺度时序及全局注意力机制，有效提取EEG信号中的多尺度时间模式，并同步捕获长短程时空依赖。为进一步提升性能，STC利用时空卷积聚合丰富的时空表征。实验表明，所提MHANet在三个数据集上达到当前最优性能，且可训练参数量仅为最先进模型的三分之一。代码已开源：https://github.com/fchest/MHANet。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。