Performance of data-driven inner speech decoding with same-task EEG-fMRI data fusion and bimodal models
This work addresses the problem of enhancing brain-computer interface accuracy for inner speech decoding, though it is incremental as it builds on existing hybridisation methods.
The study tackled decoding inner speech from brain signals by fusing EEG and fMRI data, finding that bimodal fusion strategies improved decoding performance when the data exhibited underlying structure, with performance varying across participants.
Decoding inner speech from the brain signal via hybridisation of fMRI and EEG data is explored to investigate the performance benefits over unimodal models. Two different bimodal fusion approaches are examined: concatenation of probability vectors output from unimodal fMRI and EEG machine learning models, and data fusion with feature engineering. Same task inner speech data are recorded from four participants, and different processing strategies are compared and contrasted to previously-employed hybridisation methods. Data across participants are discovered to encode different underlying structures, which results in varying decoding performances between subject-dependent fusion models. Decoding performance is demonstrated as improved when pursuing bimodal fMRI-EEG fusion strategies, if the data show underlying structure.