Enhanced Humans
Reconstructing Spoken Sentences From Brain Activity Patterns
- The present work is the first that decodes continuously spoken speech and transforms it into a textual representation. For this purpose, cortical information is combined with linguistic knowledge and machine learning algorithms to extract the most likely word sequence.
- The brain activity was recorded in the USA from 7 epileptic patients, who participated voluntarily in the study during their clinical treatments. An electrode array was placed on the surface of the cerebral cortex (electrocorticography (ECoG)) for their neurological treatment.
- While patients read aloud sample texts, the ECoG signals were recorded with high resolution in time and space. Later on, the researchers in Karlsruhe analyzed the data to develop Brain-to-Text.
Keep up. Subscribe to our daily newsletter.
Read This Next
Future Society
Facebook is Looking to Help You Find Your Next Job
Future Society
Politicians Are Now Facing Legal Action For Sharing Extremists’ Posts on Social Media
Future Society
EU to Internet Companies: You Have Three Months to Get Rid of Extremist Content
Future Society
Obama: Social Media Is “Shaping Our Culture in Powerful Ways”
Future Society
To Kick Bots off Social Media, Congress Might Have to Get Involved
Next Article
////////////