Method of contextual speech decoding from the brain

A method, comprising:

• receiving, via a neural recording device, neural signal data from a brain of a subject;
• processing the neural signal data to detect a speech event associated with an attempt or intent of producing a speech or textual output;
• receiving, via an external device separate from the neural recording device, information indicative of context associated with the speech event or the subject;
• extracting from the information one or more context-related features pertaining to the setting, circumstances or events that precede follow, or are simultaneous with the speech event, wherein the context-related features are distinct from the attempted or intended speech or textual output;
• decoding the speech or textual output from the neural signal data using the one or more context-related features as input to an artificial neural network having two or more layers, wherein the artificial neural network utilizes the one or more context-related features to determine a likelihood of one or more predicted speech or textual outputs;
• and
• communicating instructions to a device to produce text on a screen, an audio output, or both based on the decoded speech or textual output.