Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2602.23960 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912930854862848 |
|---|---|
| author | Xu, Xiran Yan, Yujie Wu, Xihong Chen, Jing |
| author_facet | Xu, Xiran Yan, Yujie Wu, Xihong Chen, Jing |
| contents | How natural speech is represented in the brain constitutes a major challenge for cognitive neuroscience, with cortical envelope-following responses playing a central role in speech decoding. This paper presents our approach to the Speech Detection task in the LibriBrain Competition 2025, utilizing over 50 hours of magnetoencephalography (MEG) signals from a single participant listening to LibriVox audiobooks. We introduce the proposed Sequential Hierarchical Integration Network for EEG and MEG (SHINE) to reconstruct the binary speech-silence sequences from MEG signals. In the Extended Track, we further incorporated auxiliary reconstructions of speech envelopes and Mel spectrograms to enhance training. Ensemble methods combining SHINE with baselines (BrainMagic, AWavNet, ConvConcatNet) achieved F1-macro scores of 0.9155 (Standard Track) and 0.9184 (Extended Track) on the leaderboard test set. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23960 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SHINE: Sequential Hierarchical Integration Network for EEG and MEG Xu, Xiran Yan, Yujie Wu, Xihong Chen, Jing Sound Artificial Intelligence How natural speech is represented in the brain constitutes a major challenge for cognitive neuroscience, with cortical envelope-following responses playing a central role in speech decoding. This paper presents our approach to the Speech Detection task in the LibriBrain Competition 2025, utilizing over 50 hours of magnetoencephalography (MEG) signals from a single participant listening to LibriVox audiobooks. We introduce the proposed Sequential Hierarchical Integration Network for EEG and MEG (SHINE) to reconstruct the binary speech-silence sequences from MEG signals. In the Extended Track, we further incorporated auxiliary reconstructions of speech envelopes and Mel spectrograms to enhance training. Ensemble methods combining SHINE with baselines (BrainMagic, AWavNet, ConvConcatNet) achieved F1-macro scores of 0.9155 (Standard Track) and 0.9184 (Extended Track) on the leaderboard test set. |
| title | SHINE: Sequential Hierarchical Integration Network for EEG and MEG |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2602.23960 |