MOV-AAD is a CC-BY-4.0 multimodal lab dataset (Columbia / naplab; Interspeech 2026; arXiv 2610.04180) with 50 adults recorded during moving-conversation auditory-attention tasks. Alongside 64-channel EEG and eye tracking, it releases synchronized raw PPG, SpO₂, heart rate, EDA, respiration, skin temperature and triaxial accelerometry at 1200 Hz on g.tec hardware (~87 minutes per participant). Data are public on Hugging Face (naplabdataset/mov-aad, ~320 GB) with loader code at github.com/naplab/MOV-AAD.
Official dataset repository for MOV-AAD, a large-scale multimodal dataset designed for investigating selective auditory attention decoding (AAD), spatial audio localization, and cross-modal peripheral physiological tracking during dynamic, naturalistic conversations with moving sound sources.
Verbatim fromHugging Face· Description from the Hugging Face card; licence as stated on the card
No model in the hub reports results on this dataset yet.
Icons show the form factor: we have no openly licensed or manufacturer-cleared photo of these exact devices yet.
MOV-AAD: A Large-Scale Multimodal Dataset for Auditory Attention Decoding During Moving Conversations [Data set]. (n.d.). https://doi.org/10.21437/Interspeech.2026-3556
@misc{movaadeegppgspo2movaad,
title = {{MOV-AAD: A Large-Scale Multimodal Dataset for Auditory Attention Decoding During Moving Conversations}},
doi = {10.21437/Interspeech.2026-3556}
}Cite the dated snapshot 2026-10 for a fixed, reproducible version. Please also cite the original publications listed above.
ChatPPG. (2026). MOV-AAD: A Large-Scale Multimodal Dataset for Auditory Attention Decoding During Moving Conversations: dataset record (Version 2026-10) [Data set]. ChatPPG Research Hub. https://chatppg.com/research/datasets/mov-aad-eeg-ppg-spo2-moving-conversations
@misc{chatppg_dataset_mov_aad_eeg_ppg_spo2_moving_conversations,
author = {{ChatPPG}},
title = {{MOV-AAD: A Large-Scale Multimodal Dataset for Auditory Attention Decoding During Moving Conversations: dataset record}},
year = {2026},
month = nov,
version = {2026-10},
howpublished = {\url{https://chatppg.com/research/datasets/mov-aad-eeg-ppg-spo2-moving-conversations}},
note = {ChatPPG Research Hub, Snapshot 2026-10, https://chatppg.com/research/snapshots/2026-10}
}cff-version: 1.2.0 message: "If you use this resource, please cite it as below." type: dataset title: "MOV-AAD: A Large-Scale Multimodal Dataset for Auditory Attention Decoding During Moving Conversations: dataset record" authors: - name: "ChatPPG" url: "https://chatppg.com/research/datasets/mov-aad-eeg-ppg-spo2-moving-conversations" repository-artifact: "https://chatppg.com/research/snapshots/2026-10" version: "2026-10" date-released: "2026-11-09"
Record updated
Apnea Burden-Guided Framework: Enhancing Out-of-Distribution Generalization in PPG-Based Sleep Apnea CharacterizationSame task: SpO₂arXiv preprint · 2026
BrainCodes: A Lightweight EEG Foundation Model over Discrete Neural CodesSame task: Mental workloadarXiv 2610.29320v1 · 2026
A Multimodal Dataset for Investigating Working Memory in Presence of MusicSame task: Mental workloadPPG · ECG · IMU
Simultaneous physiological measurements with five devices at different cognitive and physical loadsSame task: RespirationPPG · ECG · IMU
SRF cognitive adaptationSame task: Mental workload19-ch EEG + EDA + finger BVP + respiration (30 subj, Nexus-32, rest-period autonomic segments)30 subjects · PPG · EDA · Resp