← Back to all news
arXiv AI By Frederik M{\o}llskov Trier, Xiaopeng Mao, Sadasivan Puthusserypady

Decoding Imagined Speech: A Strictly Subject-Independent Approach Using EEG

Read the original on arXiv AI →

This study evaluates imagined speech decoding from EEG using a strictly subject‑independent framework. Two pipelines—time‑domain statistical features and frequency‑domain spectral bandpower—were compared with a random forest classifier; the spectral approach achieved higher trial‑wise accuracy (49.03 % vs. 37.97 %). Feature selection revealed that only a few frequency bands carried most discriminative information, providing a solid baseline for future cross‑subject BCI research.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Jul 28

Bayesian Complete-Pooling in Cross-Subject Classification for Motor Imagery Electroencephalogram

arXiv:2607. 22980v1 Announce Type: new Abstract: Brain-computer interfaces (BCIs) have long sought calibration-free operation, but classifiers are typically benchmarked by discrimination alone, blind to whether predicted probabilities are well calibrated - a meaningful gap given nonstationary electroencephalogram (EEG) signals and the risk of overconfident point-estimate classifiers under distribution shift.

By Ethan Davis
More like this →
arXiv AI
Aug 25

Cross-Subject Generalization in Decoding Perceived Speech from Non-Invasive Brain Recordings

The paper introduces a Cross-Subject Perceived Speech Decoding (CPSD) framework that tackles the challenge of decoding perceived speech from non‑invasive brain recordings across different subjects. CPSD uses a two‑stage training process: first, contrastive learning pre‑trains a source model on multiple subjects to capture shared representations; second, personal specialization fine‑tunes the model for a target subject by extracting consistent components and further training on that subject’s data. A Positional Encoding‑based Spatial Attention (PESA) module is added to remap MEG/EEG data into a standardized reference space, improving cross‑subject consistency. Evaluations on three datasets (Armeni 2022, PKUEEG 2025, Broderick 2018) show that CPSD outperforms baseline methods by more than 6.8%, 15.4%, and 15.8% in Top‑10 accuracy, demonstrating its effectiveness, efficiency, and robustness.

By Aoke Zhang, Bo Wang, Xihong Wu, Heping Cheng, Jing Chen
fine-tuning
More like this →