A new mind-reading device can turn brainwaves into speech



[ad_1]

    A new mind-reading device can turn brainwaves into speech



SAN FRANCISCO, California – For the first time, scientists believe they have found ways to generate complete sentences based on brain activity, thus opening the way to a technology that can be used by people with speech disorders.

>> Read more new trends

A new study by the San Francisco Weill Institute of Neuroscience at the University of California, for which scientists have inserted electrodes on five epilepsy patients, recorded them by reading 101 sentences. high and showed how the brain regions involved in the language reacted.

They then mapped how the voice tracks of individuals moved during their conversation, creating a simulated voice path for each participant.

The "MIND-READING" Machine Can Help Restore Speech Among Victims Of Stroke | Science | Information https://t.co/DC6JYfZrBV pic.twitter.com/EbTADtrm72

– Dady Blog (@ TRENDINGHITS1) April 25, 2019

This is not really a machine to read thoughts, but rather an interpreter of craniofacial gestures, it's an incredible breakthrough https://t.co/kECPQuOoAZ

– Felipe Alcantara (@ laboratorymol1) April 25, 2019

>> Related: 5 things to know about ALS and Stephen Hawking's survival for decades

Because there are about 100 muscles used to produce speech and they are controlled by a combination of neurons that trigger at the same time, according to New Scientist, it is not as easy to map the signals of an electrode to a muscle to determine the result. that is why scientists have designed machine learning algorithms to detect brain activity and ultimately produce a speech similar to that of the participant.

The next step was to test the speech understanding. To do this, the researchers played the new voices produced by the machine to 1,755 English speakers and asked them to transcribe what they had heard.

Get closer to the mind reading w tech!
The machine that reads your mind (Kinda) and discusses (Sorta) https://t.co/wnIGWEygLh via @ WIRED

– ?✌? (@NicoMcLane) April 25, 2019

According to the study, published Wednesday in the journal Nature Neuroscience, the listeners perfectly transcribed 43% of the tests and could understand on average 69% of the words spoken.

>> Related: Jamie Dupree, silenced by illness, gathers new voice from old cbadettes

"We still have a long way to go to imitate spoken language," Josh Chartier, a UCSF researcher, told Newsweek. "We are good enough to synthesize slower vocal sounds like" sh "and" z ", as well as to maintain the rhythms and intonations of speech, as well as the speaker's gender and identity, but some of the the steepest sounds such as "b and p a little blurry. "

@digitaljournal
A new algorithm paves the way for a potential "brain reading". It is thanks to the machine learning technology that allows the identification of music tracks from the fMRI badyzes of the auditor https://t.co/g1NQ0J3S6Y.

– UnicornIndia (@unicornindia) March 12, 2018

On the applicability of brain reading for predictive human-machine interfaces in robotics http://t.co/LK4k8w8y6g pic.twitter.com/3cMJUzwxxE

– PLOS ONE (@PLOSONE) December 16, 2013

Although the two-step process, which involves electrodes to detect brain motion and computer algorithms to reproduce speech, is not ready for clinical parameters, the accuracy produced by their artificial coder is a significant improvement over what is currently available and could prove useful for people who were able to speak but were losing their ability, usually caused by diseases such as Lou Gehrig's disease, autism, certain cancers, dementia and other neurological disorders. Indeed, the device depends on control motor functions, which are always sent to the brain even if an individual is paralyzed.

>> Related: Study: Professions related to Lou Gehrig's disease and Parkinson's disease

"People who can not move their arms and legs have learned to control robotized limbs with their brains," said Chartier. "We hope that someday people with speech disorders will be able to relearn how to speak using this brain-controlled artificial voice."

Tre Azam has developed a brain-reading machine to treat mental health problems. # DS15 pic.twitter.com/Vn2e41pDNs

– Jamie Stantonian (@jamiestantonian) May 13, 2015

#MotivationMonday SUUUUPER Cool Brain Reading Machine for Children http://t.co/P2WOIt9TZN pic.twitter.com/u34KlXLGba

– University of Houston (@UHouston) August 17, 2015

© 2019 Cox Media Group.

[ad_2]
Source link