用脑电数据解码发音，提出双路径模型提升识别精度。
CIPHER: Conformer-based Inference of Phonemes from High-density EEG
- 结合脑电反应与宽带频谱特征的双路径模型
- 11类辅音-元音-辅音发音识别错误率达67%以上
- 强调实验设计对干扰因素的控制，适合作为基准研究
从头皮脑电（EEG）中解码语音信息仍面临信噪比低和空间模糊的挑战。本文提出CIPHER（基于Conformer的高密度脑电发音推断模型），采用双路径架构，分别利用事件相关电位（ERP）特征和宽带动态谱分析（DDA）系数。在OpenNeuro ds006104数据集（24名参与者，含经颅磁刺激同步实验）上，二分类发音任务接近完美性能，但易受声学起始分离性和磁刺激靶点阻断等混杂因素影响。在主任务11类辅音-元音-辅音（CVC）发音识别中，全研究2留一被试交叉验证（LOSO）下表现显著降低：真实词错误率（WER）为ERP 0.671 ± 0.080，DDA 0.688 ± 0.096，表明精细发音区分能力有限。因此，本工作定位为基准与特征对比研究，而非端到端脑电转文本系统，并将神经表征结论严格限定于混杂因素可控的证据。
原文摘要 · Abstract (English)
Decoding speech information from scalp EEG remains difficult due to low SNR and spatial blurring. We present CIPHER (Conformer-based Inference of Phonemes from High-density EEG Representations), a dual-pathway model using (i) ERP features and (ii) broadband DDA coefficients. On OpenNeuro ds006104 (24 participants, two studies with concurrent TMS), binary articulatory tasks reach near-ceiling performance but are highly confound-vulnerable (acoustic onset separability and TMS-target blocking). On the primary 11-class CVC phoneme task under full Study 2 LOSO (16 held-out subjects), performance is substantially lower (real-word WER: ERP 0.671 +/- 0.080, DDA 0.688 +/- 0.096, indicating limited fine-grained discriminability. We therefore position this work as a benchmark and feature-comparison study rather than an EEG-to-text system, and we constrain neural-representation claims to confound-controlled evidence.
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。