nm000224 NEMAR-native dataset
Imagined speech EEG dataset — short and long words (Nguyen et al. 2017)
Preprocessed 64-channel EEG recordings from six healthy participants performing imagined speech of a short word ('in') versus a long word ('cooperate'). The data were band-pass and notch filtered and cleaned of EOG artifacts. They were used to classify imagined speech with Riemannian manifold covariance features and relevance vector machines for brain-computer interface applications. The dataset is re-hosted in BIDS format through the MOABB benchmark collection.
EEG