MEGConformer: Conformer-Based MEG Decoder for Robust Speech and Phoneme Classification
Abstract
The Conformer-based decoders adapted for MEG signals achieved high performance in Speech Detection and Phoneme Classification tasks using task-specific augmentations and normalization techniques.
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.
Community
Hello!
Here are the relevant links:
- Paper: arXiv:2512.01443
- Code: GitHub
- Checkpoints in HF:
- NeurIPS Competition: LibriBrain 2025
We welcome any questions, feedback, or ideas for improvement!
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Elementary, My Dear Watson: Non-Invasive Neural Keyword Spotting in the LibriBrain Dataset (2025)
- MultiDiffNet: A Multi-Objective Diffusion Framework for Generalizable Brain Decoding (2025)
- Adaptive Split-MMD Training for Small-Sample Cross-Dataset P300 EEG Classification (2025)
- RatioWaveNet: A Learnable RDWT Front-End for Robust and Interpretable EEG Motor-Imagery Classification (2025)
- Open Source State-Of-the-Art Solution for Romanian Speech Recognition (2025)
- Mispronunciation Detection and Diagnosis Without Model Training: A Retrieval-Based Approach (2025)
- A Penny for Your Thoughts: Decoding Speech from Inexpensive Brain Signals (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 2
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper