Abstract
We propose MEBM-Speech, a multi-scale enhanced neural decoder for speech activity detection from non-invasive magnetoencephalography (MEG) signals. Built upon the BrainMagic backbone, MEBM-Speech integrates three complementary temporal modeling mechanisms: a multi-scale convolutional module for short-term pattern extraction, a bidirectional LSTM (BiLSTM) for long-range context modeling, and a depthwise separable convolutional layer for efficient cross-scale feature fusion. A lightweight temporal jittering strategy and average pooling further improve onset robustness and boundary stability. The model performs continuous probabilistic decoding of MEG signals, enabling fine-grained detection of speech versus silence states - an ability crucial for both cognitive neuroscience and clinical applications. Comprehensive evaluations on the LibriBrain Competition 2025 Track1 benchmark demonstrate strong performance, achieving an average F1 macro of 89.3% on the validation set and comparable results on the official test leaderboard. These findings highlight the effectiveness of multi-scale temporal representation learning for robust MEG-based speech decoding.
Abstract (translated)
我们提出了MEBM-Speech，这是一种用于从非侵入性脑磁图（MEG）信号中检测语音活动的多尺度增强神经解码器。基于BrainMagic骨干网络，MEBM-Speech集成了三种互补的时间建模机制：一个多尺度卷积模块用于短期模式提取，一个双向长短时记忆网络（BiLSTM）用于长距离上下文建模，以及一个深度可分离卷积层用于高效的跨尺度特征融合。一种轻量级的时间抖动策略和平均池化进一步提高了起始点的鲁棒性和边界稳定性。该模型对MEG信号进行连续的概率解码，能够精细地检测语音与静默状态——这一能力对于认知神经科学和临床应用都至关重要。在LibriBrain Competition 2025 Track1基准上的全面评估显示了其强大的性能，在验证集上平均F1宏评分达到了89.3%，并在官方测试排行榜上取得了类似的结果。这些发现突显了多尺度时间表示学习对于基于MEG的语音解码的有效性。
URL
https://arxiv.org/abs/2603.02255
