MEGConformer: Conformer-Based MEG Decoder for Robust Speech and Phoneme Classification
By: Xabier de Zuazo, Ibon Saratxaga, Eva Navas
Potential Business Impact:
Helps computers understand spoken words from brain waves.
We present Conformer-based decoders for the LibriBrain 2025 PNPL competition, targeting two foundational MEG 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, surpassing the competition baselines and ranking within the top-10 in both tasks. For further implementation details, the technical documentation, source code, and checkpoints are available at https://github.com/neural2speech/libribrain-experiments.
Similar Papers
The 2025 PNPL Competition: Speech Detection and Phoneme Classification in the LibriBrain Dataset
Machine Learning (CS)
Lets paralyzed people talk using brain signals.
LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale
Machine Learning (CS)
Helps computers understand spoken words from brain waves.
Pretrained Conformers for Audio Fingerprinting and Retrieval
Sound
Finds sounds in noisy recordings quickly.