MEGConformer: Conformer-Based MEG Decoder for Robust Speech and Phoneme Classification

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 Libri-Brain 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 F1macro for model selection, our best systems achieved 88.9% (Speech) and 73.6% (Phoneme) on the leaderboard, winning the Phoneme Classification Standard track.