{"schema_version":"0.4.0","doc_type":"dataset","dataset_id":"on007602","name":"EEG-Speech Brain Decoding Dataset","description":"This dataset comprises EEG recordings paired with vocal audio data collected during an overt speech production task, in which participants vocalized visually presented text. Sessions are organized by recording date, with multiple runs per day, supporting research on brain-to-speech decoding and neural correlates of speech production. The dataset is intended to facilitate development and evaluation of EEG-based speech brain-computer interface models.","source":"nemar","recording_modality":["EEG"],"bids_version":null,"license":"CC0","authors":[{"name":"Motoshige Sato","name_type":"Personal"},{"name":"Masakazu Inoue","name_type":"Personal","orcid":"0009-0009-2888-936X"},{"name":"Kenichi Tomeoka","name_type":"Personal"},{"name":"Ilya Horiguchi","name_type":"Personal"},{"name":"Eri Hatakeyama","name_type":"Personal","orcid":"0009-0001-8285-9091"},{"name":"Yuya Kita","name_type":"Personal"},{"name":"Atsushi Yamamoto","name_type":"Personal"},{"name":"Ippei Fujisawa","name_type":"Personal"},{"name":"Shuntaro Sasai","name_type":"Personal","orcid":"0000-0002-9941-6510"}],"keywords":[{"term":"Electroencephalography","subject_scheme":"MeSH","value_uri":"http://id.nlm.nih.gov/mesh/D004569"},{"term":"speech decoding"},{"term":"brain-computer interface"},{"term":"overt speech production"},{"term":"EEG"},{"term":"audio recordings"}],"related_identifiers":[{"identifier":"https://github.com/nemarDatasets/on007602","identifier_type":"URL","relation_type":"IsDescribedBy"},{"identifier":"https://nemar.org/dataset/on007602","identifier_type":"URL","relation_type":"IsDescribedBy"},{"identifier":"10.1088/1741-2552/ae54d0","identifier_type":"DOI","relation_type":"IsDescribedBy"},{"identifier":"10.18112/openneuro.ds007602.v1.0.1","identifier_type":"DOI","relation_type":"IsDerivedFrom"}],"contributors":[],"dates":[],"rights":[{"rights":"CC0","rights_uri":null,"rights_identifier":"CC0","rights_identifier_scheme":"SPDX"}],"language":null,"funding":[{"funder_name":"JST","award_number":"JPMJMS2012","award_title":"Moonshot R&D","funder_identifier":null,"funder_identifier_type":null,"award_uri":null}],"tasks":["speechopen"],"datatypes":["eeg"],"sessions":["20230829","20230830","20230831","20230901","20230904","20240821","20240822","20240829","20240902","20240906","20250522","20250523","20250526","20250527","20250528"],"sessions_count":15,"demographics":{"subjects_count":3,"age_min":null,"age_max":null},"data_summary":{"total_files":476,"size_bytes":53309495417,"size_human":"49.6 GB","recording_count":113,"recordings_unavailable":0,"total_recording_duration":159071,"recording_duration_range":{"min":167,"max":5180},"channel_count_range":{"min":139,"max":140}},"signal_defaults":{"sampling_frequency":1200,"power_line_frequency":50,"reference":"FCz","recording_type":null,"channel_system":"other","placement_scheme":"Custom montage based on 10-20 system"},"provenance":{"latest_snapshot":"v1.0.0","publish_date":"2026-06-30 14:12:49"},"external_links":{"dataset_doi":"10.82901/nemar.on007602","github_url":"https://github.com/nemarDatasets/on007602"},"extensions":{"nemar":{"versions":[{"version":"v1.0.0","doi":"10.82901/nemar.on007602.v1.0.0","created_at":"2026-06-30 14:12:49","manifest_url":"/on007602/v1.0.0/manifest.json"}],"bids_index":{"version":"v1.0.0","subjects":{"sub-01":{"sessions":["20230829","20230830","20230831","20230901","20230904"],"modalities":{"eeg":{"tasks":{"speechopen":{"runs":["01","02","03","04","05","06","07"]}}}}},"sub-02":{"sessions":["20250522","20250523","20250526","20250527","20250528"],"modalities":{"eeg":{"tasks":{"speechopen":{"runs":["01","02","03","04","05","06","07","08","09","10","11","12","13","14","15","16","17"]}}}}},"sub-03":{"sessions":["20240821","20240822","20240829","20240902","20240906"],"modalities":{"eeg":{"tasks":{"speechopen":{"runs":["01","02","03","04","05"]}}}}}}},"pipeline_stage":"validated","data_complete":1,"bytes_present":53306605500,"recordings_measured":113}}}