EEG foundation models pretrained on thousands of hours have shown large gains over task-specific networks for motor imagery, seizure detection, sleep staging, and emotion recognition, but their transfer to speech decoding-arguably the most demanding non-invasive BCI application-remains untested. We present the first systematic benchmark of EEG foundation models against strong convolutional baselines for speech decoding, using two corpora: UGR-MINDVOICE (overt and covert Iberian Spanish) and BCI Competition 2020 Track 3 (imagined speech). We compare two foundation models (LaBraM, EEGMamba) against three established baselines (EEGNet, ShallowFBCSPNet, EEGConformer) under a unified preprocessing and fine-tuning protocol. Large-scale EEG pretraining yields no consistent advantage over a 16K-parameter CNN on speech tasks, indicating that current general-purpose EEG pretraining does not yet transfer to speech production and motivating speech-specific foundation models.
This work presents a new Spanish-language electroencephalography (EEG) dataset for imagined speech, designed to support research in braincomputer interface (BCI) applications for assistive communication. A structured experimental protocol was developed to guide the acquisition process, incorporating auditory comprehens...
Luis-Raul Sigala-Gonzalez, G. Ramírez-Alonso, J. Ramírez-Quintana et al.· IEEE Latin America Transacti...· 0 citations
This study presents a transparent baseline investigation of a multi-class imagined speech EEG dataset under a strictly subject-independent evaluation framework, providing a strong basis for future brain-computer interface studies targeting improved cross-subject generalization in EEG-based imagined speech decoding.
Frederik Møllskov Trier, Xiao-Peng Mao, S. Puthusserypady· 0 citations
This thesis compares three standard architectures a compact convolutional network (EEGNet), an LSTM recurrent network, and a self-attention Transformer against a hybrid model that feeds a shared convolutional front end into parallel recurrent and self-attention branches and fuses them before classification.
Findings show that healthy-benchmark performance does not ensure transfer to stroke EEG, and translation of EEG foundation models to pseudo-online or real-time rehabilitation BCIs should therefore include target-domain adaptation and subject-level assessment of temporal informativeness, spatial sensitivity, and physiol...
Anh T. Nguyen, Zihan Sun, Michelle J. Johnson· 0 citations
This study contributes to the advancement of trustworthy, next-generation brain–computer interfaces and provides a practical basis for assistive communication tools serving individuals with paralysis, amyotrophic lateral sclerosis, locked-in syndrome, and other conditions that disrupt natural speech.
Abhimanyu Singh, Edith Paulin S· International Journal For Mu...· 0 citations
A comprehensive taxonomy of MI EEG cross-variability decoding studies from 2020 to 2025 is presented, systematically organizing advances in deep learning and transfer learning and critically evaluate core algorithmic approaches, including Convolutional Neural Networks, transformers, feature alignment, domain adaptation...
Li-Jun Wang, Yue-Ying Zhou, Peng-Pai Wang et al.· Frontiers in Neuroscience· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
