LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Özdogan, Miran, Landau, Gilad, Elvers, Gereon, Jayalath, Dulhan, Somaiya, Pratik, Mantegna, Francesco, Woolrich, Mark, Jones, Oiwi Parker
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910982338510848
author Özdogan, Miran
Landau, Gilad
Elvers, Gereon
Jayalath, Dulhan
Somaiya, Pratik
Mantegna, Francesco
Woolrich, Mark
Jones, Oiwi Parker
author_facet Özdogan, Miran
Landau, Gilad
Elvers, Gereon
Jayalath, Dulhan
Somaiya, Pratik
Mantegna, Francesco
Woolrich, Mark
Jones, Oiwi Parker
contents LibriBrain represents the largest single-subject MEG dataset to date for speech decoding, with over 50 hours of recordings -- 5$\times$ larger than the next comparable dataset and 50$\times$ larger than most. This unprecedented `depth' of within-subject data enables exploration of neural representations at a scale previously unavailable with non-invasive methods. LibriBrain comprises high-quality MEG recordings together with detailed annotations from a single participant listening to naturalistic spoken English, covering nearly the full Sherlock Holmes canon. Designed to support advances in neural decoding, LibriBrain comes with a Python library for streamlined integration with deep learning frameworks, standard data splits for reproducibility, and baseline results for three foundational decoding tasks: speech detection, phoneme classification, and word classification. Baseline experiments demonstrate that increasing training data yields substantial improvements in decoding performance, highlighting the value of scaling up deep, within-subject datasets. By releasing this dataset, we aim to empower the research community to advance speech decoding methodologies and accelerate the development of safe, effective clinical brain-computer interfaces.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02098
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale
Özdogan, Miran
Landau, Gilad
Elvers, Gereon
Jayalath, Dulhan
Somaiya, Pratik
Mantegna, Francesco
Woolrich, Mark
Jones, Oiwi Parker
Machine Learning
LibriBrain represents the largest single-subject MEG dataset to date for speech decoding, with over 50 hours of recordings -- 5$\times$ larger than the next comparable dataset and 50$\times$ larger than most. This unprecedented `depth' of within-subject data enables exploration of neural representations at a scale previously unavailable with non-invasive methods. LibriBrain comprises high-quality MEG recordings together with detailed annotations from a single participant listening to naturalistic spoken English, covering nearly the full Sherlock Holmes canon. Designed to support advances in neural decoding, LibriBrain comes with a Python library for streamlined integration with deep learning frameworks, standard data splits for reproducibility, and baseline results for three foundational decoding tasks: speech detection, phoneme classification, and word classification. Baseline experiments demonstrate that increasing training data yields substantial improvements in decoding performance, highlighting the value of scaling up deep, within-subject datasets. By releasing this dataset, we aim to empower the research community to advance speech decoding methodologies and accelerate the development of safe, effective clinical brain-computer interfaces.
title LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale
topic Machine Learning
url https://arxiv.org/abs/2506.02098