acm-header
Sign In

Communications of the ACM

ACM TechNews

Speech Recognition From Brain Activity


View as: Print Mobile App Share:
Brain activity recorded by electrocorticography (blue circles). From the activity patterns (blue/yellow), spoken words can be recognized.

A multidisciplinary team of researchers at the Karlsruhe Institute of Technology and the Wadsworth Center have reconstructed brain waves associated with speech processes into text.

Credit: CSL/Karlsruhe Institute of Technology

Researchers from the Karlsruhe Institute of Technology (KIT) and the Wadsworth Center have reconstructed spoken words from brain waves associated with speech processes and transformed the speech into text.

There has been speculation concerning whether humans can communicate with machines through brain activity alone, says the KIT Cognitive Systems Lab's Tanja Schultz. "As a major step in this direction, our recent results indicate that both single units in terms of speech sounds as well as continuously spoken sentences can be recognized from brain activity," she says.

The work by the interdisciplinary team of experts in informatics, neuroscience, and medicine marks the first time continuously spoken speech has been decoded and generated into a textual representation.

The team recorded the electrocorticography signals of epileptic patients reading aloud sample texts. The researchers then analyzed the data to develop the brain-to-text system.

From Karlsruhe Institute of Technology
View Full Article

 

Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account