Neuroprosthetics have demonstrated the potential to decode speech from intracranial brain signals, and hold promise for one day returning the ability to speak to those who have lost it. However, data in this domain is scarce, highly variable, and costly to label for supervised modeling. In order to address these constraints, we present brain2vec, a transformer-based approach for learning feature representations from intracranial electroencephalogram data. Brain2vec combines a self-supervised learning methodology, neuroanatomical positional embeddings, and the contextual representations of transformers to achieve three novelties: (1) learning from unlabeled intracranial brain signals, (2) learning from multiple participants simultaneously, all while (3) utilizing only raw unprocessed data. To assess our approach, we use a leave-one-participant-out validation procedure to separate brain2vec's feature learning from the holdout participant's speech-related supervised classification tasks. With only two linear layers, we achieve 90% accuracy on a canonical speech detection task, 42% accuracy on a more challenging 4-class speech-related behavior recognition, and 53% accuracy when applied to a 10-class, few-shot word classification task. Combined with visualizations of unsupervised class separation in the learned features, our results evidence brain2vec's ability to learn highly generalized representations of neural activity without the need for labels or consistent sensor location.
published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.• Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal.If the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the "Taverne" license above, please follow below link for the End User
To inform selection of a control range around the Public Health Service’s recommended 0.7 mg/L drinking water fluoride concentration to prevent tooth decay, CDC’s Water Fluoridation Reporting System data for 2006–2010 and 2015 were analyzed. Monthly average concentration data from 4,251 fluoride-adjusted community water systems for 191,266 of 255,060 system-months (2006–2010) were compared to control ranges 0.6 mg/L to 0.2 mg/L wide. Percentages of system-months within control ranges ≥0.4 mg/L wide (e.g., ±0.2 mg/L) were >83% versus 68% for 0.2 mg/L wide (±0.1 mg/L). In 2015, 70% of adjusted systems maintained averages within ±0.1 mg/L of their system’s annual average for 9 of 12 months, 67% used the 0.7 mg/L target and 45% used it with a ±0.1 mg/L control range. Adoption of the 0.7 mg/L target was underway but not completed in 2015. Control ranges narrower than ±0.2 mg/L may be feasible for monthly average fluoride concentration.
Numerous state-of-the-art solutions for neural speech decoding and synthesis incorporate deep learning into the processing pipeline. These models are typically opaque and can require significant computational resources for training and execution. A deep learning architecture is presented that learns input bandpass filters that capture task-relevant spectral features directly from data. Incorporating such explainable feature extraction into the model furthers the goal of creating end-to-end architectures that enable automated subject-specific parameter tuning while yielding an interpretable result. The model is implemented using intracranial brain data collected during a speech task. Using raw, unprocessed timesamples, the model detects the presence of speech at every timesample in a causal manner, suitable for online application. Model performance is comparable or superior to existing approaches that require substantial signal preprocessing and the learned frequency bands were found to converge to ranges that are supported by previous studies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.