Unlocking Speech Through Brain Implant & Machine Learning

Click For Summary

Discussion Overview

The discussion centers around a research study involving a brain implant and machine learning to decode thoughts into speech for individuals with anarthria. It explores the implications of this technology, the methodology used, and the results obtained from the study.

Discussion Character

  • Exploratory, Technical explanation, Debate/contested

Main Points Raised

  • Some participants highlight the ability to record thoughts from a person with anarthria using a network of electrodes and machine learning algorithms.
  • One participant provides a link to the original research paper for further reading.
  • Several participants mention access issues with the New York Times article, indicating it may be behind a paywall for some.
  • A participant shares specific results from the study, noting a median decoding rate of 15.2 words per minute and a word error rate of 25.6%.
  • Another participant humorously relates the study's word classification accuracy to their own typing skills.

Areas of Agreement / Disagreement

Participants express mixed experiences regarding access to the articles, and while some share results from the study, there is no consensus on the implications or future applications of the technology discussed.

Contextual Notes

Some participants may have limited access to the original articles, which could affect the depth of discussion. The results shared are based on specific metrics from the study, but further context on the methodology or broader implications remains unaddressed.

Who May Find This Useful

Readers interested in neuroscience, machine learning applications in healthcare, and the intersection of technology and speech rehabilitation may find this discussion relevant.

gleem
Science Advisor
Education Advisor
Messages
2,731
Reaction score
2,230
TL;DR
An experimental system connecting electrodes implanted in a brain can display words that a person thinks of saying.
In a collaboration of several institutions researchers have been able to record the thoughts of a person with a brain stem stroke resulting in anarthria (an inability to articulate speech) by mplanting network of electrodes in the brain and using a machine learning algorithm to decode the thoughts of words and display them on a computer screen.
https://www.nytimes.com/2021/07/14/...3473&user_id=799d953295eabb464706b7f2130bc45f

 
  • Like
Likes   Reactions: 256bits, berkeman, pbuk and 1 other person
Computer science news on Phys.org
I see the article as being behind a paywall
 
phinds said:
I see the article as being behind a paywall
I'm able to access the NYT article in the OP link.
 

RESULTS​

We decoded sentences from the participant’s cortical activity in real time at a median rate of 15.2 words per minute, with a median word error rate of 25.6%. In post hoc analyses, we detected 98% of the attempts by the participant to produce individual words, and we classified words with 47.1% accuracy using cortical signals that were stable throughout the 81-week study period.That's about the state of my typing skills.
 
  • Like
Likes   Reactions: Keith_McClary

Similar threads

  • · Replies 2 ·
Replies
2
Views
1K
Replies
3
Views
1K
Replies
2
Views
3K
  • · Replies 2 ·
Replies
2
Views
1K
Replies
4
Views
1K
  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 2 ·
Replies
2
Views
1K
Replies
4
Views
1K
  • · Replies 2 ·
Replies
2
Views
1K
  • · Replies 1 ·
Replies
1
Views
2K