Neural Spelling: A Spell-Based BCI System for Language Neural Decoding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Xiaowei, Zhou, Charles, Duan, Yiqun, Zhao, Ziyi, Do, Thomas, Lin, Chin-Teng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917303854039040
author Jiang, Xiaowei
Zhou, Charles
Duan, Yiqun
Zhao, Ziyi
Do, Thomas
Lin, Chin-Teng
author_facet Jiang, Xiaowei
Zhou, Charles
Duan, Yiqun
Zhao, Ziyi
Do, Thomas
Lin, Chin-Teng
contents Brain-computer interfaces (BCIs) present a promising avenue by translating neural activity directly into text, eliminating the need for physical actions. However, existing non-invasive BCI systems have not successfully covered the entire alphabet, limiting their practicality. In this paper, we propose a novel non-invasive EEG-based BCI system with Curriculum-based Neural Spelling Framework, which recognizes all 26 alphabet letters by decoding neural signals associated with handwriting first, and then apply a Generative AI (GenAI) to enhance spell-based neural language decoding tasks. Our approach combines the ease of handwriting with the accessibility of EEG technology, utilizing advanced neural decoding algorithms and pre-trained large language models (LLMs) to translate EEG patterns into text with high accuracy. This system show how GenAI can improve the performance of typical spelling-based neural language decoding task, and addresses the limitations of previous methods, offering a scalable and user-friendly solution for individuals with communication impairments, thereby enhancing inclusive communication options.
format Preprint
id arxiv_https___arxiv_org_abs_2501_17489
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Spelling: A Spell-Based BCI System for Language Neural Decoding
Jiang, Xiaowei
Zhou, Charles
Duan, Yiqun
Zhao, Ziyi
Do, Thomas
Lin, Chin-Teng
Human-Computer Interaction
Artificial Intelligence
Brain-computer interfaces (BCIs) present a promising avenue by translating neural activity directly into text, eliminating the need for physical actions. However, existing non-invasive BCI systems have not successfully covered the entire alphabet, limiting their practicality. In this paper, we propose a novel non-invasive EEG-based BCI system with Curriculum-based Neural Spelling Framework, which recognizes all 26 alphabet letters by decoding neural signals associated with handwriting first, and then apply a Generative AI (GenAI) to enhance spell-based neural language decoding tasks. Our approach combines the ease of handwriting with the accessibility of EEG technology, utilizing advanced neural decoding algorithms and pre-trained large language models (LLMs) to translate EEG patterns into text with high accuracy. This system show how GenAI can improve the performance of typical spelling-based neural language decoding task, and addresses the limitations of previous methods, offering a scalable and user-friendly solution for individuals with communication impairments, thereby enhancing inclusive communication options.
title Neural Spelling: A Spell-Based BCI System for Language Neural Decoding
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2501.17489