EEGdash›OpenNeuro›DS007591

Iss. 7591 · 3 subjects · 21 recordings · CC0

Dataset Brief · Delineating neural contributions to EEG-based speech decoding

DS007591: eeg dataset, 3 subjects#

Delineating neural contributions to EEG-based speech decoding

Citation: Motoshige Sato, Yasuo Kabe, Sensho Nobe, Akito Yoshida, Masakazu Inoue, Mayumi Shimizu, Kenichi Tomeoka, Shuntaro Sasai (—). Delineating neural contributions to EEG-based speech decoding. 10.18112/openneuro.ds007591.v1.0.1

3-participant EEG dataset — Delineating neural contributions to EEG-based speech decoding.

Data & curation Motoshige Sato · Yasuo Kabe · Sensho Nobe · Akito Yoshida · Masakazu Inoue · Mayumi Shimizu · …
Funding JST, Moonshot R&D Grant Number JPMJMS2012

EEG · 139 ch256 HzBIDS 1.9.03 tasks6 sessionsHealthyMotor

Layer 01Study

What was asked

Hypothesis, independent & dependent variables, paradigm, cohort, and the editorial caveats around what the recordings can and cannot answer.

Layer 02Signal · BIDS

What was recorded

Sidecars, channels & electrodes, coordinate system, event semantics, and quality stats from the NEMAR pipeline when available.

Layer 03Training · ML

What you can train on

Recommended access modes — MNE Raw, braindecode windows, PyTorch DataLoader — plus the targets the metadata makes addressable.

§ 01Access · Get started

Quickstart#

Get Started

Install

pip install eegdash

Access the data

from eegdash.dataset import DS007591

dataset = DS007591(cache_dir="./data")
# Get the raw object of the first recording
raw = dataset.datasets[0].raw
print(raw.info)

Query & Filter

Filter by subject

dataset = DS007591(cache_dir="./data", subject="01")

Advanced query

dataset = DS007591(
    cache_dir="./data",
    query={"subject": {"$in": ["01", "02"]}},
)

Iterate recordings

for rec in dataset:
    print(rec.subject, rec.raw.info['sfreq'])

Cite This Dataset

If you use this dataset in your research, please cite the original authors.

BibTeX

@dataset{ds007591,
  title = {Delineating neural contributions to EEG-based speech decoding},
  author = {Motoshige Sato and Yasuo Kabe and Sensho Nobe and Akito Yoshida and Masakazu Inoue and Mayumi Shimizu and Kenichi Tomeoka and Shuntaro Sasai},
  doi = {10.18112/openneuro.ds007591.v1.0.1},
  url = {https://doi.org/10.18112/openneuro.ds007591.v1.0.1},
}

§ 02Study · The README

About This Dataset#

128-channel EEG recordings during speech production tasks.

Participants produced one of 5 color words (green, magenta, orange, violet, yellow)

under three speech conditions: overt, minimally overt, and covert.

Delineating neural contributions to EEG-based speech decoding

Overview

Each trial consists of 5 repetitions of the same word (1.25 sec per repetition).

Channel layout (139 channels total)

Channels 1-128: EEG

View full README

Delineating neural contributions to EEG-based speech decoding

Overview

Each trial consists of 5 repetitions of the same word (1.25 sec per repetition).

Channel layout (139 channels total)

Channels 1-128: EEG

Channels 129-130: DISPLAY (bipolar pair, misc)

Channels 131-132: MIC (bipolar pair, misc)

Channels 133-134: EOG (bipolar pair)

Channels 135-136: EMG upper orbicularis oris (bipolar pair)

Channels 137-138: EMG lower orbicularis oris (bipolar pair)

Channel 139: TRIGGER (marks trial onsets)

Session types

calibration: Offline data collection for decoder training

online: Real-time decoding with trained decoder

Preprocessing note

The EEG channels were recorded with a 10x preamp gain.

Raw values have been converted to Volts (×1e-6).

Code

Code for data loading, preprocessing, and decoding models is available at: arayabrain/uhd-gmail-public

§ 03Cohort · Participants

Cohort#

Dataset Statistics#

Channel counts: 139 ch (n=21 recordings)

Sampling frequencies: 256.0 Hz (n=21 recordings)

Total recording duration: 6 h 46 min

§ 04Signal · Electrodes & trace

Signal · Electrodes & live trace#

Fig. 01 Signal & montage 139 ch · EEG · 256 Hz · 3 subjects, 21 recordings

Live trace viewer — sub-1 · ses-20230511 · task-minimallyovert · run-02

Showing one representative recording out of 3 subjects and 21 recordings in this dataset. Browse the full set on OpenNeuro; drop any other _eeg.{set,edf,bdf,vhdr} file onto the viewer (or pass ?eeg=<url>) to inspect it.

Electrode layout — EEG · 128 sensors — 128 channels

NEMAR Processing Statistics#

The plots below are generated by NEMAR’s automated EEG pipeline. The histogram shows pipeline success for data cleaning and ICA decomposition, the percentage of data frames and EEG channels retained after artefact removal, line noise per channel (RMS, dB), and the age/gender distribution of participants.

HED event descriptors word cloud

§ 05Manifest · BIDS tree

Manifest#

File Explorer#

Browse the BIDS file structure of this dataset. Records are fetched on demand from the EEGDash catalog the first time you open the explorer.

Recordings—

Files—

Subjects—

Modalities—

Click to load file structure…

§ 06API · Programmatic access

API Reference#

Signature

eegdash.dataset

class

eegdash.dataset.DS007591(cache_dir, query=None, s3_bucket=None, **kwargs)

Bases: EEGDashDataset

Author (year)Sato2026_Delineating

Canonical—

Importable asDS007591 · Sato2026_Delineating

Sourceeegdash/dataset/registry.py · [source ↗]

class eegdash.dataset.DS007591(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

Delineating neural contributions to EEG-based speech decoding

Study:: ds007591 (OpenNeuro)
Author (year):: Sato2026_Delineating
Canonical:: —

Also importable as: DS007591, Sato2026_Delineating.

Modality: eeg; Experiment type: Motor; Subject type: Healthy. Subjects: 3; recordings: 21; tasks: 3.

Parameters:

cache_dir (str | Path) – Directory where data are cached locally.
query (dict | None) – Additional MongoDB-style filters to AND with the dataset selection. Must not contain the key dataset.
s3_bucket (str | None) – Base S3 bucket used to locate the data.
**kwargs (dict) – Additional keyword arguments forwarded to EEGDashDataset.

data_dir#

Local dataset cache directory (cache_dir / dataset_id).

Type:: Path

query#

Merged query with the dataset filter applied.

Type:: dict

records#

Metadata records used to build the dataset, if pre-fetched.

Type:: list[dict] | None

Notes

Each item is a recording; recording-level metadata are available via dataset.description. query supports MongoDB-style filters on fields in ALLOWED_QUERY_FIELDS and is combined with the dataset filter. Dataset-specific caveats are not provided in the summary metadata.

References

OpenNeuro dataset: https://openneuro.org/datasets/ds007591 NeMAR dataset: https://nemar.org/dataexplorer/detail?dataset_id=ds007591 DOI: https://doi.org/10.18112/openneuro.ds007591.v1.0.1

Examples

>>> from eegdash.dataset import DS007591
>>> dataset = DS007591(cache_dir="./data")
>>> recording = dataset[0]
>>> raw = recording.load()

__init__(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

save(path: str, overwrite: bool = False, offset: int = 0)[source]#

Save datasets to files by creating one subdirectory for each dataset:

path/
    0/
        0-raw.fif | 0-epo.fif
        description.json
        raw_preproc_kwargs.json (if raws were preprocessed)
        window_kwargs.json (if this is a windowed dataset)
        window_preproc_kwargs.json  (if windows were preprocessed)
        target_name.json (if target_name is not None and dataset is raw)
    1/
        1-raw.fif | 1-epo.fif
        description.json
        raw_preproc_kwargs.json (if raws were preprocessed)
        window_kwargs.json (if this is a windowed dataset)
        window_preproc_kwargs.json  (if windows were preprocessed)
        target_name.json (if target_name is not None and dataset is raw)

Parameters:

path (str) –

Directory in which subdirectories are created to store
-raw.fif | -epo.fif and .json files to.
overwrite (bool) – Whether to delete old subdirectories that will be saved to in this call.
offset (int) – If provided, the integer is added to the id of the dataset in the concat. This is useful in the setting of very large datasets, where one dataset has to be processed and saved at a time to account for its original position.

Access modesMNE → braindecode → PyTorch → ML

.rawMNE Raw object — standard tools (filter, epoch, ICA, plot_psd).mne

BaseConcatDatasetEach record is a lazy BaseDataset from braindecode — windowed via create_windows_from_events.braindecode

DataLoaderWraps the windowed dataset into a PyTorch DataLoader; supports parallel workers and on-the-fly augmentations.pytorch

Zarr cacheOptional braindecode Zarr mirror for fast resume; persisted to cache_dir.zarr

Hugging FaceNo per-dataset mirror published yet — browse the EEGDash org listing for sibling datasets. See the datasets loader API.huggingface

Croissant 1.0Machine-readable JSON-LD descriptor — DS007591.croissant.json (MLCommons schema, ingestible by PyTorch / TensorFlow / JAX).mlcommons

Examples using EEGDashcurated · start here

Find datasets with the EEGDash APIQuery the catalogue, filter by task or modality, list candidates.

Load one EEG recordingResolve a single record to an MNE Raw with channels and events.

EEG recording to PyTorch DataLoaderWrap braindecode windows in a DataLoader for model training.

Preprocess EEG and create windowsFilter, resample, epoch — and persist the windowed dataset.

Save and reload prepared dataCache a windowed dataset to disk and reattach it without recompute.

Download a dataset locallyPrefetch BIDS files to a local cache and validate the layout.

Swap any load_dataset(...) call for ds007591 to reproduce the tutorial on this dataset.

Citation

Motoshige Sato, Yasuo Kabe, Sensho Nobe, Akito Yoshida, Masakazu Inoue, … (n.d.). Delineating neural contributions to EEG-based speech decoding. 10.18112/openneuro.ds007591.v1.0.1

Provenance

¹Contributed to openneuro in BIDS format.

²Curated & ingested by the EEGDash catalog; see CITATION.cff for canonical reference.

³Persistent identifier: 10.18112/openneuro.ds007591.v1.0.1.

Related & sibling datasets

DS006317EEG · 2 subj DS007262EEG · 18 subj DS004521EEG · 34 subj DS004502EEG · 48 subj DS006159EEG · 61 subj

+ 1 more — see See Also below →

BIDS

BIDS 1.9.0

Sidecars

events · channels · electrodes · coordsystem · eeg.json

Provenance

CC0 · 10.18112/openneuro.ds007591.v1.0.1

Machine-readable

schema.org/Dataset · Croissant

Mirrors

OpenNeuro · NEMAR · HF org

Dataset ID	`DS007591`
Title	Delineating neural contributions to EEG-based speech decoding
Author (year)	`Sato2026_Delineating`
Canonical	—
Importable as	`DS007591`, `Sato2026_Delineating`
Year	—
Authors	Motoshige Sato, Yasuo Kabe, Sensho Nobe, Akito Yoshida, Masakazu Inoue, Mayumi Shimizu, Kenichi Tomeoka, Shuntaro Sasai
License	CC0
Citation / DOI	doi:10.18112/openneuro.ds007591.v1.0.1
Source links	OpenNeuro \| NeMAR \| Source URL

DS007591: eeg dataset, 3 subjects#

Quickstart#

About This Dataset#

Cohort#

Dataset Statistics#

Signal · Electrodes & live trace#

NEMAR Processing Statistics#

Manifest#

File Explorer#

API Reference#

Citation

Provenance

Related & sibling datasets

See Also#