New System Generates Speech from Brain Physiology

Click For Summary
SUMMARY

Scientists have demonstrated a proof of principle study where brain recordings are used to generate understandable speech. This process involves invasive recordings of brain activity related to speech production, utilizing recurrent neural networks to decode cortical activity into articulatory movements and subsequently into speech acoustics. While the technology shows promise for future clinical applications, its current invasive nature limits trial subject availability and raises concerns about medical conditions affecting speech motor areas. The study highlights the potential for transferrable decoded articulatory representations across different speakers.

PREREQUISITES
  • Understanding of recurrent neural networks (RNNs)
  • Knowledge of brain-computer interface (BCI) technology
  • Familiarity with speech production mechanisms
  • Awareness of ethical considerations in invasive medical procedures
NEXT STEPS
  • Research advancements in brain-computer interface technology
  • Explore the implications of recurrent neural networks in speech synthesis
  • Investigate the effects of language differences on articulatory representation decoding
  • Study the ethical considerations surrounding invasive neural recording techniques
USEFUL FOR

Neuroscientists, speech-language pathologists, researchers in artificial intelligence, and professionals interested in brain-computer interfaces will benefit from this discussion.

BillTre
Science Advisor
Gold Member
Messages
2,768
Reaction score
12,163
TL;DR
Scientists published a study describe using information from brain recordings to generate understandable speech.
Scientists described using information from brain recordings to generate understandable speech in a proof of principle study.
Invasive recordings of brain activity normally involved in the production of speech sounds, at the level of controlling muscle movement, have been associated with the speech sounds produced. This has allowed recordings of brain activity to drive the generation of understandable machine generated speech. The invasive nature of the electrode placement (inside the skull) makes finding trial subjects more difficult.
In the long run, this process may be developed to being clinically useful, but it is not ready yet.
Medical problems affecting the speech motor areas (where the recordings are made) could rule its use out in particular cases.
Here is a NY Times article on it.
Here is the original article in Nature which is behind a paywall.
 
  • Like
  • Love
Likes   Reactions: DennisN, atyy and berkeman
Biology news on Phys.org
BillTre said:
Summary: Scientists published a study describe using information from brain recordings to generate understandable speech.
When I first read the summary I found it hard to believe, but then I read the abstract,

Abstract said:
Recurrent neural networks first decoded directly recorded cortical activity into representations of articulatory movement, and then transformed these representations into speech acoustics.

which I suppose means that the system has to be "taught" depending on which person is using it, which makes the technology understandable and feasible to me.

And further down the abstract reads

Abstract said:
Decoded articulatory representations were highly conserved across speakers, enabling a component of the decoder to be transferrable across participants.

which I find very interesting and a bit surprising. And this makes me wonder if and how different the conserved decoded articulatory representations would be for different languages, e.g. English and, let's say Spanish.

Anyway, this is amazing and inspiring research! Thanks for posting!
 
  • Like
Likes   Reactions: atyy and BillTre

Similar threads

Replies
15
Views
5K
  • · Replies 1 ·
Replies
1
Views
3K
  • · Replies 2 ·
Replies
2
Views
1K
Replies
2
Views
2K
  • · Replies 13 ·
Replies
13
Views
4K
  • · Replies 2 ·
Replies
2
Views
5K
  • · Replies 20 ·
Replies
20
Views
24K
Replies
9
Views
4K
  • · Replies 47 ·
2
Replies
47
Views
10K
  • · Replies 1 ·
Replies
1
Views
3K