MOV-AAD：移动对话中听觉注意力解码的大规模多模态数据集
MOV-AAD: A Large-Scale Multimodal Dataset for Auditory Attention Decoding During Moving Conversations
浏览论文内容
中文总结 AI 辅助
MOV-AAD是一个大规模多模态数据集，结合64通道EEG和多种生理信号，用于研究移动自然对话中的听觉注意力解码，支持鲁棒AAD和多模态注意力建模。
中文摘要 AI 辅助
听觉注意力解码（AAD）通常在静态、简化的语音场景下进行评估，这些场景与日常聆听环境匹配度较低。我们引入了MOV-AAD，一个用于研究移动、自然对话条件下听觉注意力的大规模数据集。MOV-AAD结合了64通道脑电图（EEG）与同步的生理记录，包括眼动追踪、呼吸、皮肤电反应、心率、外周血氧饱和度、体温、身体运动和光电容积脉搏波，从而能够分析注意力和聆听努力的跨模态神经与生理标记。该数据集采用更具生态效度的聆听范式，包含动态移动的对话语音源以及注意力参与的行为测量。MOV-AAD支持在现实空间动态条件下对鲁棒AAD、多模态注意力建模、聆听努力和受试者间神经反应的研究，为自然聆听中的选择性听觉注意力基准测试提供了资源。
英文摘要
Auditory attention decoding (AAD) is often evaluated on static, simplified speech scenes that poorly match everyday listening. We introduce MOV-AAD, a large-scale dataset for studying auditory attention under moving, naturalistic conversations. MOV-AAD combines 64-channel EEG with synchronized physiological recordings, including eye tracking, respiration, galvanic skin response, heart rate, peripheral oxygen saturation, body temperature, body motion, and photoplethysmography, enabling analysis of cross-modal neural and physiological markers of attention and listening effort. This dataset uses a more ecologically valid listening paradigm with dynamically moving conversational speech sources and behavioral measures of attentional engagement. MOV-AAD supports research on robust AAD in realistic spatial dynamics, multimodal attention modeling, listening effort, and intersubject neural responses, providing a resource for benchmarking selective auditory attention in naturalistic listening.
发表机构
- Columbia University（哥伦比亚大学）
机构由 AI 辅助整理，请以论文原文为准。
