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...
By Gilad D. Landau, Dulhan Jayalath, Oiwi Parker Jones
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.
By Francesco Mantegna, Dulhan Jayalath, Gereon Elvers, Tasha Kim, Benjamin Ballyk, Alex Fung, SungJun Cho, Teyun Kwon, Luisa Kurth, Miran \"Ozdogan, Gilad Landau, Pratik Somaiya, Natalie Voets, Mark Woolrich, Oiwi Parker Jones
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.
By Benjamin Ballyk, Teyun Kwon, Miran \"Ozdogan, Oiwi Parker Jones
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.
By Zehui Feng, Weichuan Wang, Xiaohan Chen, Cuntai Guan, Ting Han
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.
By Dulhan Jayalath, Oiwi Parker Jones
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.
By Gaorui Zhang, Zhizhang Yuan, Jialan Yang, Junru Chen, Fanqi Shen, Li Meng, Yang Yang