Confidence-Aware Neural Decoding of Overt Speech from EEG: Toward Robust Brain-Computer Interfaces
This work addresses the need for trustworthy and robust brain-computer interfaces for communication systems, though it appears incremental as it builds on existing methods with enhancements like calibration and selective classification.
The paper tackled the problem of decoding spoken commands from EEG for brain-computer interfaces by developing a confidence-aware framework that improves reliability and selective performance, achieving more accurate probability estimates and balanced per-class acceptance compared to baselines.
Non-invasive brain-computer interfaces that decode spoken commands from electroencephalogram must be both accurate and trustworthy. We present a confidence-aware decoding framework that couples deep ensembles of compact, speech-oriented convolutional networks with post-hoc calibration and selective classification. Uncertainty is quantified using ensemble-based predictive entropy, top-two margin, and mutual information, and decisions are made with an abstain option governed by an accuracy-coverage operating point. The approach is evaluated on a multi-class overt speech dataset using a leakage-safe, block-stratified split that respects temporal contiguity. Compared with widely used baselines, the proposed method yields more reliable probability estimates, improved selective performance across operating points, and balanced per-class acceptance. These results suggest that confidence-aware neural decoding can provide robust, deployment-oriented behavior for real-world brain-computer interface communication systems.