Problem
Research questions and friction points this paper is trying to address.
Auditory Attention Decoding
EEG dataset
multi-talker environments
ecological validity
neuro-steered hearing technologies
A multi-scenario EEG dataset for auditory attention decoding in naturalistic multi-talker environments
🤖 AI Summary
This study addresses the limitation of existing EEG-based auditory research, which relies on idealized laboratory paradigms that fail to capture the complex acoustic and semantic structures inherent in natural multi-speaker environments. To bridge this gap, we introduce a novel dynamic "sound bubble" paradigm and present the SoundBubble-EEG dataset, comprising 25 hours of 128-channel high-density EEG recordings from 30 participants performing selective attention tasks across three real-world scenarios: restaurants, homes, and meetings. Furthermore, decoding benchmarks are established using neural speech tracking algorithms. By bridging the divide between constrained experimental settings and complex real-world auditory environments, this work provides a standardized evaluation platform that supports cross-scenario generalization for auditory attention decoding (AAD) and neuro-steered hearing technologies.
📝 Abstract
Understanding how the brain selectively follows relevant speech amid competing voices is a central challenge in auditory neuroscience and a key step toward neuro-steered hearing technologies. However, most open-source Electroencephalography (EEG) datasets for Auditory Attention Decoding (AAD) use idealized single-competing-talker paradigms that oversimplify the acoustic, spatial, and semantic structure of everyday communication. To capture this ecological complexity, we introduce the SoundBubble-EEG dataset: a high-density 128-channel EEG resource comprising more than 25 hours of recordings from 30 participants. The paradigm requires listeners to selectively attend to a dynamic target speaker group, a designated "sound bubble", amid competing multi-speaker distractor bubbles across three realistic scenarios: a restaurant, a home TV viewing, and a meeting discussion. By bridging the gap between constrained laboratory protocols and real-world auditory scenes, this dataset enables investigations of multi-talker speech comprehension, neural speech tracking, and cross-scenario generalization. It also provides a benchmark for AAD algorithms under realistic acoustic and semantic variability and may support auditory neuroscience and the development of neuro-steered hearing technologies.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Auditory Attention Decoding
EEG dataset
multi-talker environments
ecological validity
cross-scenario generalization
🔎 Similar Papers
No similar papers found.
