A High-Density EEG Dataset for Stimulus-Driven Auditory Attention

2026-10-01

AI Summary

This study addresses the challenge of decoding auditory attention in instruction-free, multi-source competitive listening scenarios, overcoming limitations of existing approaches that rely solely on acoustic saliency or predefined targets. To this end, we construct a dataset under the Spontaneous Auditory Attention Decoding (SAAD) paradigm and propose a computational framework integrating stimulus priority with EEG evidence. Methodologically, this work is the first to combine generalizable sound priority with trial-specific neural variability, leveraging high-density EEG, the Bradley-Terry model, and multiscale gated decision-level fusion to model spontaneous attention. Experimental results demonstrate that behavioral prediction AUC improves from 0.577 to 0.718, validating the core predictive value of centro-temporal lateralized signals beyond mere acoustic asymmetry.

Abstract

Stimulus-driven auditory attention determines which sound gains priority when multiple sources compete without an explicit listening goal, yet most computational studies focus either on acoustic salience or on decoding predefined attended targets. This study investigates instruction-free auditory competition using the Stimulus-driven Auditory Attention (SAAD) paradigm and develops a neurophysiologically informed framework that integrates stimulus-derived sound priority with trial-specific EEG evidence. Behavioral analysis using a Bradley--Terry model showed that sound priority estimated from previous competitions generalized to unseen sound pairings, improving held-out prediction from an AUC of 0.577 to 0.718. EEG analysis further revealed mid-to-late centro-temporal lateralization associated with the reported selection side, with neural information remaining predictive beyond acoustic asymmetry. Guided by these findings, the proposed model first estimates a latent priority for each competing sound and forms relative stimulus evidence from their difference. A multi-scale EEG pathway with complementary signed and power-based readouts then extracts trial-specific neural evidence, which is incorporated through gated decision-level integration. The framework is evaluated using mirror-constrained and pairing-held-out protocols, together with representative acoustic, EEG, multimodal baselines, and systematic ablations. The results support a computational account in which spontaneous auditory selection reflects the interaction between generalizable stimulus priority and trial-specific neural variability.

Problem

• stimulus-driven auditory attention
• auditory competition
• EEG
• sound priority
• computational modeling

Innovation

• Stimulus-driven auditory attention
• High-density EEG
• Bradley-Terry model
• Multi-scale EEG pathway
• Gated decision-level integration