CerebroVoice: Bilingual sEEG Speech Dataset
- Participants
- 2
- Size
- 1.87 GB
- Version
- v1.0.0
- Updated
- Jul 10, 2026
100 results for "handwriting decoding" · page 6 of 10 · ranked by relevance
…EEG data), and run decoding (analyse_decoding.m; reliant on pre-processed…
This dataset contains EEG recordings from 10 healthy adults performing a P300 speller task using a 6x6 character matrix, under two stimulus conditions (Famous Faces overlay and Inverting). Data were collected across two sessions per subject with three runs each, using a 32-channel g.tec EEG system at 256 Hz. The dataset is a BIDS-formatted derivative generated via MOABB from the original data reported in Speier et al. (2017), which compared classification approaches for the P300 speller using language models.
[ and auditory stimulation (tones to left and right ears), with occasional face stimuli requiring motor responses. Structural MRI data from a 1.5 T Siemens scanner and Freesurfer-derived anatomical derivatives are included, providing a comprehensive reference dataset for MEG/EEG analysis and method development.
[. Participants received auditory and visual cues to imagine speaking each vowel, with 64-channel EEG data acquired at 256 Hz. The dataset includes 2,400 trials generating 7,200 overlapping 2-second epochs (8 subjects × 300 trials × 3 overlapping epochs per trial) analyzed using Riemannian manifold-based feature extraction and relevance vector machine classification for brain-computer interface applications, achieving approximately 49% mean accuracy across a 10-fold cross-validation scheme.