Fig. 4: LME approach models neural activity as a combination of spectrographic and phonemic label features.
From: Acoustic and language-specific sources for phonemic abstraction from speech
For each stimulus waveform, spectrograms are computed and time-aligned phonemic-level transcriptions are assigned. Transcriptions are additionally one-hot encoded (top row). Three classes of model are created from these features: a purely spectrographic model (left column), a purely phonemic label model (right column), and a model containing both feature sets (middle column). For each band of neural activity, mixed effects models are fit. Model weights are used to reconstruct a predicted response for each band, and the correlation between the predicted and recorded neural response is calculated.
