Performance of data-driven inner speech decoding with same-task EEG-fMRI data fusion and bimodal models

TL;DR

This study investigates how combining EEG and fMRI data improves inner speech decoding, showing that bimodal fusion strategies enhance performance when data exhibit underlying structure, with results varying across individuals.

Contribution

It introduces and compares two bimodal fusion approaches for inner speech decoding using EEG-fMRI data, highlighting the importance of data structure for performance gains.

Findings

Bimodal fusion improves decoding performance over unimodal models.

Data structure influences the effectiveness of fusion strategies.

Subject-dependent differences affect fusion model performance.

Abstract

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.