用轻量Conformer模型从脑磁图信号中精准识别语音和音素，性能领先。
MEGConformer: Conformer-Based MEG Decoder for Robust Speech and Phoneme Classification
- 采用轻量Conv投影层+任务头，适配306通道原始脑磁图数据
- 语音检测达88.9%准确率，音素分类达65.8%（领先榜单）
- 针对分布偏移设计实例归一化，适合脑机接口研究者参考
从非侵入式脑磁图（MEG）中解码语音信息是实现可扩展脑机接口的关键步骤。本文在LibriBrain 2025 PNPL基准上，针对语音检测与音素分类两个核心任务，提出紧凑型基于Conformer的解码器。模型直接处理306通道原始MEG信号，结合轻量卷积投影层与任务特定输出头。针对语音检测，引入面向MEG的SpecAugment进行数据增强；针对音素分类，采用反平方根类权重与动态分组加载器处理每100样本平均的输入。此外，简单的实例级归一化有效缓解了测试集上的分布偏移问题。使用官方标准赛道划分及F1-macro指标选择模型，最优系统在语音检测任务上取得88.9%的分数，在音素分类任务上达到65.8%，夺得音素分类标准赛道冠军。完整技术文档、源代码与模型检查点见https://github.com/neural2speech/libribrain-experiments。
原文摘要 · Abstract (English)
Decoding speech-related information from non-invasive MEG is a key step toward scalable brain-computer interfaces. We present compact Conformer-based decoders on the LibriBrain 2025 PNPL benchmark for two core tasks: Speech Detection and Phoneme Classification. Our approach adapts a compact Conformer to raw 306-channel MEG signals, with a lightweight convolutional projection layer and task-specific heads. For Speech Detection, a MEG-oriented SpecAugment provided a first exploration of MEG-specific augmentation. For Phoneme Classification, we used inverse-square-root class weighting and a dynamic grouping loader to handle 100-sample averaged examples. In addition, a simple instance-level normalization proved critical to mitigate distribution shifts on the holdout split. Using the official Standard track splits and F1-macro for model selection, our best systems achieved 88.9% (Speech) and 65.8% (Phoneme) on the leaderboard, winning the Phoneme Classification Standard track. For further implementation details, the technical documentation, source code, and checkpoints are available at https://github.com/neural2speech/libribrain-experiments.
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。