Speech decoding on the basis of single words has so far been limited to intracranial recordings. Scientists demonstrated the feasibility of non-invasive language decoding using EEG and MEG, finding that more training data consistently increases model performance
#neuroskyence #compneuro #neuroAI
While deep learning has enabled the decoding of language from intracranial brain recordings, achieving this with non-invasive recordings remains an open challenge. Here the authors introduce a deep le...
