arXiv cs.CL· Keondo Park, Arthur Delhaye, Younghoon Na, Hyun-Woo Shin, Hyung-Sin Kim·· 9 小时前AI 评分29
Sleep2Word:通过时长感知词化实现外周信号到 EEG 的翻译
Sleep2Word: Peripheral-to-EEG Translation via Duration-Aware Wordization
AI 导读
Sleep2Word 框架可将呼吸、ECG 或 PPG 信号翻译为 EEG 频谱图,通过时长感知的生理词实现跨模态转换。该方法在 9 个数据集、超 2 万例 PSG 病例上训练,在 EEG 频谱图重建、睡眠分期、觉醒检测和生存预测上均优于现有基线,全夜序列压缩率最高达 69.7%。
正文 · 原文
Abstract:Estimating full-night electroencephalography (EEG) spectrograms from peripheral measurements could extend EEG-informed sleep analysis to recordings acquired without EEG. This task requires compact representations of signals with different temporal structures. We introduce Sleep2Word, a framework for translating respiration, electrocardiography (ECG), or photoplethysmography (PPG) into EEG spectrograms through duration-aware physiological words. Building on context-dependent chunking, Sleep2Word groups physiological embeddings into variable-duration chunks and jointly quantizes their content and duration into modality-specific wordbooks. A block-autoregressive translator then predicts target EEG word identities and occurrence-specific duration refinements within fixed-duration blocks. This design accommodates independent source and target wordbooks, limits temporal drift, and shortens the autoregressive decoding path. Trained on over 20K PSG cases across 9 datasets, Sleep2Word consistently outperforms existing spectrogram generation baselines in EEG spectrogram reconstruction, sleep staging, arousal detection, and survival prediction. Compressing full night sequences by up to 69.7%, the learned words yield a favorable accuracy-compute trade-off. Sleep event analysis further shows that the learned words capture physiologically plausible associations across modalities, suggesting their potential for interpretable cross-modal analysis.
| Comments: | 10 pages, 4 figures |
| Subjects: | Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS) |
| Cite as: | arXiv:2611.21643 [cs.CL] |
| (or arXiv:2611.21643v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.21643 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Keondo Park [view email]
[v1]
Wed, 14 Oct 2026 09:29:01 UTC (7,564 KB)
来源:arXiv cs.CL · arxiv.org