Delineating neural contributions to EEG-based speech decoding

# Delineating neural contributions to EEG-based speech decoding

## Overview
128-channel EEG recordings during speech production tasks.
Participants produced one of 5 color words (green, magenta, orange, violet, yellow)
under three speech conditions: overt, minimally overt, and covert.

Each trial consists of 5 repetitions of the same word (1.25 sec per repetition).

## Channel layout (139 channels total)
- Channels 1-128: EEG
- Channels 129-130: DISPLAY (bipolar pair, misc)
- Channels 131-132: MIC (bipolar pair, misc)
- Channels 133-134: EOG (bipolar pair)
- Channels 135-136: EMG upper orbicularis oris (bipolar pair)
- Channels 137-138: EMG lower orbicularis oris (bipolar pair)
- Channel 139: TRIGGER (marks trial onsets)

## Session types
- calibration: Offline data collection for decoder training
- online: Real-time decoding with trained decoder

## Preprocessing note
The EEG channels were recorded with a 10x preamp gain.
Raw values have been converted to Volts (×1e-6).

## Code
Code for data loading, preprocessing, and decoding models is available at:
https://github.com/arayabrain/uhd-gmail-public