moabb.paradigms.SpeechImagery#

class moabb.paradigms.SpeechImagery(n_classes=None, fmin=1, fmax=100, events=None, tmin=0.0, tmax=None, baseline=None, channels=None, resample=None, scorer=None, overlap=None)[source]#

Imagined speech paradigm with broadband defaults.

Imagined speech (silently rehearsing words, phonemes, or phrases) shares the paradigm="imagery" tag with motor imagery and is decoded with the same pipeline machinery, but the relevant spectral content extends well beyond the motor mu/beta band. Defaults follow Aguilera-Rodriguez et al. (2025), Sci Data 12:1543, who report a 1-100 Hz bandpass with a 60 Hz notch on a 4-class Spanish vowel set.

Parameters:

  • fmin (float (default 1)) – cutoff frequency (Hz) for the high pass filter.

  • fmax (float (default 100)) – cutoff frequency (Hz) for the low pass filter.

:param See MotorImagery for the remaining parameters.:

On this page