Subject-independent auditory spatial attention detection based on brain topology modeling and feature distribution alignment

• Published in: Hearing research Vol. 453; p. 109104
• Main Authors: Niu, Yixiang, Chen, Ning, Zhu, Hongqing, Li, Guangqiang, Chen, Yibo
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.11.2024
• Subjects: Acoustic Stimulation; Attention - physiology; Auditory Pathways - physiology; Auditory Perception - physiology; Auditory spatial attention detection; Brain - physiology; Brain functional connectivity; Brain Waves; Domain generalization; Electroencephalogram; Electroencephalography; Graph neural network; Humans; Models, Neurological; Neural Networks, Computer; Signal Processing, Computer-Assisted; Sound Localization - physiology; Brain functional connectivity; Auditory spatial attention detection; Electroencephalogram; Graph neural network; Domain generalization
• ISSN: 0378-5955; 1878-5891; 1878-5891
• DOI: 10.1016/j.heares.2024.109104

•A subject-independent model is proposed for auditory spatial attention detection.•Mutual information-based EEG graph modeling captures brain functional connectivity.•Domain generalization enhances the generalizability of our model to unseen subjects.•The proposed model has potential applications in “neuro-steered hearing devices”. Auditory spatial attention detection (ASAD) seeks to determine which speaker in a surround sound field a listener is focusing on based on the one’s brain biosignals. Although existing studies have achieved ASAD from a single-trial electroencephalogram (EEG), the huge inter-subject variability makes them generally perform poorly in cross-subject scenarios. Besides, most ASAD methods do not take full advantage of topological relationships between EEG channels, which are crucial for high-quality ASAD. Recently, some advanced studies have introduced graph-based brain topology modeling into ASAD, but how to calculate edge weights in a graph to better capture actual brain connectivity is worthy of further investigation. To address these issues, we propose a new ASAD method in this paper. First, we model a multi-channel EEG segment as a graph, where differential entropy serves as the node feature, and a static adjacency matrix is generated based on inter-channel mutual information to quantify brain functional connectivity. Then, different subjects’ EEG graphs are encoded into a shared embedding space through a total variation graph neural network. Meanwhile, feature distribution alignment based on multi-kernel maximum mean discrepancy is adopted to learn subject-invariant patterns. Note that we align EEG embeddings of different subjects to reference distributions rather than align them to each other for the purpose of privacy preservation. A series of experiments on open datasets demonstrate that the proposed model outperforms state-of-the-art ASAD models in cross-subject scenarios with relatively low computational complexity, and feature distribution alignment improves the generalizability of the proposed model to a new subject.