Decoding Inner Speech with functional connectivity

Background: Inner-Speech (IS) based Brain-Computer Interfaces (BCIs) offer potential communication solutions for individuals with disabilities by decoding brain signals generated during speech imagination. While most IS-BCI systems rely on time-frequency EEG features, this study investigates functional connectivity—specifically, motif synchronization (MS)—to determine whether interactions between brain regions improve the discrimination of imagined words. Methods: We analyzed EEG data from the “Thinking Out Loud” dataset by Results: The model achieved an average classification accuracy of 45.8%, outperforming two of three prior studies using the same dataset while offering greater generalizability than the third (which reported higher accuracy). Conclusions: Functional connectivity features, particularly motif synchronization, show promise in IS-BCI applications by leveraging cross-regional brain interactions. This approach advances neurophysiological signal analysis and can enhance assistive technology and cognitive research. However, larger datasets are required to improve the robustness and validate scalability.