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

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.

• Publication year

  2025

• Venue

  arXiv.org

• Publication date

  2025-11-11

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.48550/arXiv.2511.07890arXiv 2511.07890
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation

  2021cited by this paper
• NeuroGrasp: Real-Time EEG Classification of High-Level Motor Imagery Tasks Using a Dual-Stage Deep Learning Framework

  2021cited by this paper
• Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting

  2021cited by this paper
• A Framework for Schizophrenia EEG Signal Classification With Nature Inspired Optimization Algorithms

  2020cited by this paper
• Denoising Diffusion Probabilistic Models

  2020cited by this paper
• Continuous EEG Decoding of Pilots’ Mental States Using Multiple Feature Block-Based Convolutional Neural Network

  2020cited by this paper
• Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling

  2018cited by this paper
• Selective Classification for Deep Neural Networks

  2017cited by this paper
• Supplementary for: Deep learning with convolutional neural networks for EEG decoding and visualization

  2017cited by this paper
• On Calibration of Modern Neural Networks

  2017cited by this paper
• EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces

  2016cited by this paper
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles

  2016cited by this paper
• Abstract Representations of Associated Emotions in the Human Brain

  2015cited by this paper
• Motion Influence Map for Unusual Human Activity Detection and Localization in Crowded Scenes

  2015cited by this paper
• Predicting BCI Subject Performance Using Probabilistic Spatio-Temporal Filters

  2014cited by this paper
• Changes of Functional and Effective Connectivity in Smoking Replenishment on Deprived Heavy Smokers: A Resting-State fMRI Study

  2013cited by this paper
• Subject and class specific frequency bands selection for multiclass motor imagery classification

  2011cited by this paper
• EEG Signal Analysis: A Survey

  2010cited by this paper
• Brain-computer interfaces for speech communication

  2010cited by this paper
• The cortical organization of speech processing

  2007cited by this paper
• Pattern recognition with support vector machines : First International Workshop, SVM 2002, Niagara Falls, Canada, August 10, 2002 : proceedings

  2002cited by this paper
• Speech Sound Representation in the Brain

  2000cited by this paper
• Integrated segmentation and recognition of handwritten numerals with cascade neural network

  1999cited by this paper
• A new recurrent neural-network architecture for visual pattern recognition

  1997cited by this paper
• Multiresolution recognition of unconstrained handwritten numerals with wavelet transform and multilayer cluster neural network

  1996cited by this paper
• Multilayer cluster neural network for totally unconstrained handwritten numeral recognition

  1995cited by this paper

• No citing papers are available for this paper.