Subject-Independent Imagined Speech Detection via Cross-Subject Generalization and Calibration

TL;DR

This paper presents a method combining cyclic inter-subject training and minimal calibration to improve imagined speech decoding across individuals, enhancing generalization and personalization in brain-computer interfaces.

Contribution

It introduces a cyclic training approach and demonstrates effective few-shot calibration, advancing cross-subject imagined speech detection.

Findings

Cyclic training improves cross-subject decoding performance.

Few-shot calibration with 10% data achieves high accuracy and AUC.

Combining training and calibration enhances BCI scalability.

Abstract

Achieving robust generalization across individuals remains a major challenge in electroencephalogram based imagined speech decoding due to substantial variability in neural activity patterns. This study examined how training dynamics and lightweight subject specific adaptation influence cross subject performance in a neural decoding framework. A cyclic inter subject training approach, involving shorter per subject training segments and frequent alternation among subjects, led to modest yet consistent improvements in decoding performance across unseen target data. Furthermore, under the subject calibrated leave one subject out scheme, incorporating only 10 % of the target subjects data for calibration achieved an accuracy of 0.781 and an AUC of 0.801, demonstrating the effectiveness of few shot adaptation. These findings suggest that integrating cyclic training with minimal calibration provides a simple and effective strategy for developing scalable, user adaptive brain computer interface systems that balance generalization and personalization.