Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

DECODING SPEECH

Translating the brain

Nature Neuroscience volume 23, pages 471–472 (2020)Cite this article

Subjects

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.

We are entering a new era of artificial intelligence. Advances in machine learning and neuroscience are giving us an opportunity to map the inner workings of the most complex thing we know of: the human brain. The application of machine learning approaches to statistical pattern extraction has increased our ability to model advanced cognition1. In parallel, electrode technology with a higher density of electrodes offers us the opportunity to learn more about the human brain than ever before2. These technological leaps promise to give us a greater understanding of neural function, especially for uniquely human aspects of cognition, including our ability to use language to share information and facilitate social bonds. Motor degenerative diseases like amyotrophic lateral sclerosis (ALS) and locked-in syndrome (LIS) can rob us of this ability, and current technologies to assist communication can be cumbersome and slow3. A promising solution is to read language directly from the brain and convert it into interpretable language. In this issue of Nature Neuroscience, Makin et al.4 use a novel approach to convert neural signals into text by taking a more holistic goal-centric approach than previous work.

This is a preview of subscription content, access via your institution

Access options

Rent or buy this article

Get just this article for as long as you need it

$39.95

Learn more

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Neural machine translation for language.

References

  1. Vu, M. T. et al. J. Neurosci. 38, 1601–1607 (2018).

    Article  CAS  Google Scholar 

  2. Viventi, J. et al. Nat. Neurosci. 14, 1599–1605 (2011).

    Article  CAS  Google Scholar 

  3. Dickerson, S. S., Stone, V. I., Panchura, C. & Usiak, D. J. Rehabil. Nurs. 27, 215–220 (2002).

    Article  Google Scholar 

  4. Makin, J.G., Moses, D.A. & Chang, E.F. Nat. Neurosci. https://doi.org/10.1038/s41593-020-0608-8 (2020).

  5. Angrick, M. et al. J. Neural Eng. 16, 036019 (2019).

    Article  Google Scholar 

  6. Pasley, B. N. et al. PLoS Biol. 10, e1001251 (2012).

    Article  CAS  Google Scholar 

  7. Orsborn, A. L. & Carmena, J. M. Front. Comput. Neurosci. 7, 157 (2013).

    Article  Google Scholar 

  8. Moses, D. A., Leonard, M. K., Makin, J. G. & Chang, E. F. Nat. Commun. 10, 3096 (2019).

    Article  Google Scholar 

  9. Kalchbrenner, N. & Blunsom, P. Recurrent continuous translation models. Empir. Methods Nat. Lang. Process. Proc. Conf. (EMNLP) 1700–1709 (2013).

  10. Herff, C. et al. Front. Neurosci. 9, 217 (2015).

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Neurosurgery, Duke Comprehensive Epilepsy Center (DCEC), Center for Cognitive Neuroscience, and Department of Psychology and Neuroscience, Duke University, Durham, NC, USA

    Gregory B. Cogan

Authors
  1. Gregory B. Cogan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Gregory B. Cogan.

Ethics declarations

Competing interests

The author declares no competing interests.

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Cogan, G.B. Translating the brain. Nat Neurosci 23, 471–472 (2020). https://doi.org/10.1038/s41593-020-0616-8

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41593-020-0616-8

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing