Brain2Qwerty v2 is a model that decodes natural sentences from real‑time magnetoencephalography (MEG) recordings, achieving an average word error rate of 39% across 22,000 sentences typed by nine subjects. The model uses character, word, and sentence‑level representations and shows that decoding accuracy improves log‑linearly with more data, narrowing the gap to intracranial brain‑computer interfaces. AI contributes by replacing hand‑crafted event detection with deep learning, fine‑tuning large language models for semantic extraction, and employing AI agents to refine the decoding pipeline through automated code development.
arXiv:2609.10296v1 Announce Type: new Abstract: Non-invasive speech decoding remains constrained by the low signal-to-noise ratio of neural recordings, which makes fine-grained reconstruction of phon...
LibriBrain100 is a new large‑scale MEG dataset for speech decoding that contains over 100 hours of high‑quality recordings while subjects listened to naturalistic continuous speech. The dataset more than doubles the size of the original LibriBrain release, with a record 80 hours from a single subject and additional 40‑minute recordings from 32 subjects. The authors demonstrate the value of deep within‑subject data and broad multi‑subject data by achieving state‑of‑the‑art word‑classification performance and showing that supervised fine‑tuning can compensate for limited per‑subject data, all supported by open‑source tools and a public competition leaderboard.
arXiv:2607. 05165v1 Announce Type: new Abstract: Non-invasive brain-to-speech decoding aims to restore communication to patients suffering from neurodegenerative disease, without the risks of neurosurgery.
The paper investigates whether large models are necessary for speech brain‑computer interfaces (BCIs) and introduces BEST, a two‑stage framework that uses hierarchical intermediate representations and a compact decoder to map neural activity directly to text. BEST achieves low word error rates (6.19% and 1.62%) on the Brain‑to‑Text ’24 and ’25 benchmarks while using only 3.85% of the parameters of comparable methods. The study also highlights that decoder scaling yields non‑monotonic gains, cross‑modal alignment is more critical than model size, and overfitting harms sequence‑level performance.
The study shows that previously reported gains in decoding spoken words from non‑invasive brain recordings can largely be replicated without any brain data, due to a timing shortcut where overlapping windows reveal word durations. By processing each window independently rather than jointly, the authors eliminate this shortcut, enabling the neural network to learn genuine brain‑based word information. This change improves performance and makes two existing strategies—aggregating predictions from multiple neural responses and incorporating a pretrained language model—significantly more effective, achieving a word error rate of 36.6% on a perceived speech benchmark.
NeuroSketch presents a practical design recipe for neural decoding, beginning with a comparative study of nine basic architectures that identifies CNN‑2D as the most effective. The recipe incorporates macro‑level gradual feature‑map expansion and early downsampling, along with micro‑level grouped convolutions, resulting in two variants—NeuroSketch‑Base (1.4M parameters) and NeuroSketch‑Large (4.2M parameters). Across nearly 5,000 experiments on eight tasks involving visual, auditory, and speech modalities and EEG, SEEG, and ECoG signals, both variants outperform ten baseline models on every task.
arXiv:2609.24095v1 Announce Type: new Abstract: While deep learning has enabled language decoding from intracranial brain recordings, extending this capability to non-invasive recordings remains an u...
arXiv:2609.36736v1 Announce Type: cross Abstract: Speech brain-computer interfaces (BCIs) aim to restore communication by transforming neural activity related to speech, language, or communicative in...
arXiv:2607. 14086v1 Announce Type: new Abstract: Robust and accurate neural decoders are integral to neurotechnologies such as brain-computer interfaces and closed-loop experiments.
iMINDBench is a new benchmark for intracranial electroencephalography (iEEG) neural decoding that evaluates models on fifteen tasks across three naturalistic movie‑watching datasets from multiple institutions. It standardizes preprocessing tracks and evaluation splits to enable consistent comparisons. The study shows that pretrained systems outperform baselines within their tracks, but strong spectral baselines remain competitive, and scaling up supervised data yields only modest or task‑dependent gains.
arXiv:2609.13507v1 Announce Type: new Abstract: Brain-computer interfaces (BCIs) decode neural activity to restore lost function. Typically, training a high-performance neural decoder requires a larg...
arXiv:2510. 15371v2 Announce Type: replace-cross Abstract: Classification of electroencephalogram (EEG) signals obtained during motor imagery (MI) has substantial application potential, including communication assistance and rehabilitation support for patients with motor impairments.