Robust representations of cortical speech and language information

Cortical recordings with high temporal resolution enable the tracking of neuronal excitation in response to stimuli. Here intra and extracranial recordings are analyzed from experiments presenting varied speech and language stimuli to human subjects. These studies demonstrate that information about speech and language is widely distributed across the brain, both spatially and temporally. Analyses using machine learning techniques can be used to track the space and time-course of performance in recognizing different words (83% on 10 spoken words), semantic categories (76% on 2 categories), etc.