News Reader.info

Access through your institution Buy or subscribe Francis Willett and colleagues — who are based at various institutes in the USA — have now created a speech-to-text brain–computer interface

that relies on four intracortical microelectrode arrays to collect signals, and a recurrent neural network and language model to decode them into words. With the system, the attempted speech

of a participant, who can no longer speak clearly due to amyotrophic lateral sclerosis, was decoded at an average rate of 62 words per minute, and with a word error rate of 23.8% for a

125,000-word vocabulary. In an alternative approach, Edward Chang and colleagues — who are based at the University of California, San Francisco, the University of California, Berkeley and

Speech Graphics in Edinburgh — have now developed a brain–computer interface that is based on a 253-channel high-density electrocorticography electrode array that is placed on the

speech-related areas of the sensorimotor cortex and superior temporal gyrus. A recurrent neural network maps the electrocorticography features to movements of the articulators that are part

of the vocal tract and then translates them into sentences using a language model. With a participant with severe limb and vocal paralysis, caused by a brainstem stroke, the approach

achieved brain-to-text decoding with a median rate of 78 words per minute and median word error rate of 25% for a 1,024-word vocabulary. This is a preview of subscription content, access via

your institution ACCESS OPTIONS Access through your institution Access Nature and 54 other Nature Portfolio journals Get Nature+, our best-value online-access subscription $32.99 / 30 days

cancel any time Learn more Subscribe to this journal Receive 12 digital issues and online access to articles $119.00 per year only $9.92 per issue Learn more Buy this article * Purchase on

SpringerLink * Instant access to full article PDF Buy now Prices may be subject to local taxes which are calculated during checkout ADDITIONAL ACCESS OPTIONS: * Log in * Learn about

institutional subscriptions * Read our FAQs * Contact customer support AUTHOR INFORMATION AUTHORS AND AFFILIATIONS * Nature Electronics https://www.nature.com/natelectron/ Katharina Zeissler

Authors * Katharina Zeissler View author publications You can also search for this author inPubMed Google Scholar CORRESPONDING AUTHOR Correspondence to Katharina Zeissler. RIGHTS AND

PERMISSIONS Reprints and permissions ABOUT THIS ARTICLE CITE THIS ARTICLE Zeissler, K. Decoding speech at speed. _Nat Electron_ 6, 645 (2023). https://doi.org/10.1038/s41928-023-01036-5

Download citation * Published: 25 September 2023 * Issue Date: September 2023 * DOI: https://doi.org/10.1038/s41928-023-01036-5 SHARE THIS ARTICLE Anyone you share the following link with

will be able to read this content: Get shareable link Sorry, a shareable link is not currently available for this article. Copy to clipboard Provided by the Springer Nature SharedIt

content-sharing initiative