MEBM-Speech: Multi-scale Enhanced BrainMagic for Robust MEG Speech Detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Songyi, Li, Linze, Zheng, Jinghua, Liang, Zifeng, Zhang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915830039576576
author Songyi, Li
Linze, Zheng
Jinghua, Liang
Zifeng, Zhang
author_facet Songyi, Li
Linze, Zheng
Jinghua, Liang
Zifeng, Zhang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_02255
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MEBM-Speech: Multi-scale Enhanced BrainMagic for Robust MEG Speech Detection
Songyi, Li
Linze, Zheng
Jinghua, Liang
Zifeng, Zhang
Sound
Artificial Intelligence
Audio and Speech Processing
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.
title MEBM-Speech: Multi-scale Enhanced BrainMagic for Robust MEG Speech Detection
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2603.02255