用脑磁图解码语音音素，实现高精度非侵入式言语脑机接口。
MEGState: Phoneme Decoding from Magnetoencephalography Signals
- 设计新架构MEGState，捕捉听觉刺激诱发的精细皮层反应。
- 在LibriBrain数据集上优于所有基线模型，多指标表现更优。
- 为非侵入式言语脑机接口提供可扩展的技术路径，适合神经工程研究者。
从非侵入性神经记录中解码语言学上有意义的表征，仍是神经言语解码的核心挑战。在现有神经成像模态中，脑磁图（MEG）提供了安全且可重复的手段来映射与言语相关的皮层动态，但其低信噪比和高时间维度仍阻碍鲁棒解码。本文提出MEGState，一种用于从MEG信号中解码音素的新架构，能够捕捉听觉刺激诱发的精细皮层响应。在LibriBrain数据集上的大量实验表明，MEGState在多个评估指标上持续优于基线模型。这些发现突显了基于MEG的音素解码在构建可扩展的非侵入式脑-计算机接口中的潜力。
原文摘要 · Abstract (English)
Decoding linguistically meaningful representations from non-invasive neural recordings remains a central challenge in neural speech decoding. Among available neuroimaging modalities, magnetoencephalography (MEG) provides a safe and repeatable means of mapping speech-related cortical dynamics, yet its low signal-to-noise ratio and high temporal dimensionality continue to hinder robust decoding. In this work, we introduce MEGState, a novel architecture for phoneme decoding from MEG signals that captures fine-grained cortical responses evoked by auditory stimuli. Extensive experiments on the LibriBrain dataset demonstrate that MEGState consistently surpasses baseline model across multiple evaluation metrics. These findings highlight the potential of MEG-based phoneme decoding as a scalable pathway toward non-invasive brain-computer interfaces for speech.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。