Confidence-Aware Neural Decoding of Overt Speech from EEG: Toward Robust Brain-Computer Interfaces

TL;DR

This paper introduces a confidence-aware neural decoding framework for EEG-based speech recognition, enhancing reliability and trustworthiness for brain-computer interfaces through uncertainty quantification and selective classification.

Contribution

It presents a novel combination of deep ensembles, post-hoc calibration, and abstain options to improve the robustness and reliability of EEG speech decoding systems.

Findings

More reliable probability estimates compared to baselines

Improved selective performance across different operating points

Balanced per-class acceptance rates

Abstract

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.