A new study shows that mapping neural signals directly to word sequences produces lower error rates in speech decoding than previous methods that use motor or auditory based features. This suggests that using higher-level language goals can aid decoding algorithms for neural speech prostheses.
This is a preview of subscription content, access via your institution
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$29.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 print issues and online access
$189.00 per year
only $15.75 per issue
Rent or buy this article
Get just this article for as long as you need it
Prices may be subject to local taxes which are calculated during checkout
Vu, M. T. et al. J. Neurosci. 38, 1601–1607 (2018).
Viventi, J. et al. Nat. Neurosci. 14, 1599–1605 (2011).
Dickerson, S. S., Stone, V. I., Panchura, C. & Usiak, D. J. Rehabil. Nurs. 27, 215–220 (2002).
Makin, J.G., Moses, D.A. & Chang, E.F. Nat. Neurosci. https://doi.org/10.1038/s41593-020-0608-8 (2020).
Angrick, M. et al. J. Neural Eng. 16, 036019 (2019).
Pasley, B. N. et al. PLoS Biol. 10, e1001251 (2012).
Orsborn, A. L. & Carmena, J. M. Front. Comput. Neurosci. 7, 157 (2013).
Moses, D. A., Leonard, M. K., Makin, J. G. & Chang, E. F. Nat. Commun. 10, 3096 (2019).
Kalchbrenner, N. & Blunsom, P. Recurrent continuous translation models. Empir. Methods Nat. Lang. Process. Proc. Conf. (EMNLP) 1700–1709 (2013).
Herff, C. et al. Front. Neurosci. 9, 217 (2015).
The author declares no competing interests.
Rights and permissions
About this article
Cite this article
Cogan, G.B. Translating the brain. Nat Neurosci 23, 471–472 (2020). https://doi.org/10.1038/s41593-020-0616-8