← Back to all news
arXiv Computation and Language By Zehui Feng, Weichuan Wang, Xiaohan Chen, Cuntai Guan, Ting Han

Do Speech BCIs Need Larger Models? Rethinking Neural Decoding beyond Scaling

Read the original on arXiv Computation and Language →

The paper investigates whether large models are necessary for speech brain‑computer interfaces (BCIs) and introduces BEST, a two‑stage framework that uses hierarchical intermediate representations and a compact decoder to map neural activity directly to text. BEST achieves low word error rates (6.19% and 1.62%) on the Brain‑to‑Text ’24 and ’25 benchmarks while using only 3.85% of the parameters of comparable methods. The study also highlights that decoder scaling yields non‑monotonic gains, cross‑modal alignment is more critical than model size, and overfitting harms sequence‑level performance.

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 Computation and Language.

Related stories

arXiv Computation and Language
Sep 30

From Neurons to Conversation: Speech Brain-Computer Interfaces

arXiv:2609.36736v1 Announce Type: cross Abstract: Speech brain-computer interfaces (BCIs) aim to restore communication by transforming neural activity related to speech, language, or communicative in...

By Moein Khajehnejad, Forough Habibollahi, Tommaso Boccato, Margarida Sousa, Michal Olak, Francesco Jamal Sheiban, Matteo Ferrante
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 →