SGAD: A State-Guided Adaptive Decision Framework for Robust EEG-Based Auditory Attention Switch Decoding

2026-08-02

AI Summary

This study addresses the limited robustness of EEG-based auditory attention decoding under non-stationary signals and confounding factors by proposing a state-guided adaptive decision framework. The approach employs causal state detection to infer attention-switching states in real time and incorporates an adaptive gating mechanism that dynamically modulates temporal smoothing to balance decoding stability and response latency. A novel six-tier evaluation protocol, combined with hierarchical cross-validation, is introduced to systematically assess the model’s generalization across varying audio stimuli, speakers, and subjects, while also uncovering the impact of data partitioning biases on performance. Experimental results demonstrate that the proposed method significantly improves decoding accuracy and robustness across multiple evaluation settings without compromising low latency.

Abstract

Achieving robust EEG-based auditory attention switch decoding (AASD) is crucial for intelligent hearing aids. However, its application is limited as EEG non-stationarity complicates sequential decision-making, and insufficient control of potential confounding factors may overestimate performance. Therefore, we propose a state-guided adaptive decision (SGAD) framework that infers attention transition states via causal state detection and dynamically modulates temporal smoothing through state-guided adaptive gating. We further introduce six hierarchical evaluation protocols to assess generalization across audio, speaker, and subject dimensions. Experimental results show that SGAD improves decoding accuracy and stability while maintaining low response latency across evaluation scenarios. Performance variations across protocols further suggest data partition-related biases. Together, these findings advance robust AASD for neuro-steered hearing applications.

Problem

• EEG-based auditory attention switch decoding
• non-stationarity
• confounding factors
• robust decoding
• sequential decision-making

Innovation

• state-guided adaptive decision
• auditory attention decoding
• EEG non-stationarity
• causal state detection
• hierarchical evaluation protocols