Evolving descriptive text of mental content from human brain activity

I have a PhD student working on EEG audio decoding. We are presently focused on a simpler subtopic: the detection of consonance and dissonance in the brain as it listens to music.

As I understand it, the big challenge with brain electrodes is that because they are implanted in a big jiggly piece of jelly, they shift out of position and/or cause localized scarring. The practical effect is that the brain-electrode interface "wears out" after a while, and you can't get useful data. Has this been solved, or are implants still temporary?

> "It wasn't perfect, but 60% of the words were judged intelligible by testers"

I don't understand this part. Are they trying to pull the audio of the words out of the brain or something? I'd think it would be easier to use a dictionary of words, and use some machine learning to try and pull out the most likely next word from the brain activity, in which case 100% of the words would be intelligible

They don't seem to mention if it is elective. An all or nothing mechanism might spell out words that the patient really didn't intend on others seeing (like "Ugh, that guy again! I can't stand the way he...")

It is pretty difficult to control your inner dialog against spontaneous and triggered thoughts.

Prediction: even if this requires surgery, unlocking inner thought will be used in criminal proceedings to establish guilt or attempt to be used to prove innocence. It will definitely be used unethically in military/intelligence interrogations until the law catches up.

"Mental content" seems way to broad for what is rather the sensorimotor part of speech.

[dead]