Loading...
Market
How many participants will be included in future EEG speech decoding studies by the end of 2024?
2
Resolution / Starting Odds
1-3 • 25%
4-6 • 25%
7-9 • 25%
10 or more • 25%
Scientific journals, Araya Inc publications
Story
Researchers Discover Scaling Law in Neural Data, Achieve 50% Accuracy in Speech Decoding Using 175 Hours of EEG
Jul 11, 2024, 05:00 AM
Researchers have discovered a scaling law in neural data that significantly improves the accuracy of speech decoding using non-invasive EEG recordings. The study, conducted by Motoshige Sato, K Tomeoka, I Horiguchi, K Arulkumaran, R Kanai, and S Sasai from Araya Inc, involved collecting 175 hours of EEG data from a single participant. The findings demonstrate that speech decoding accuracy can reach approximately 50% in a 512-phrase classification task. This breakthrough is particularly notable given the day-to-day variability in neural data and the challenges associated with non-invasive methods.
View original story
Similar markets
1-2 • 25%
3-4 • 25%
5-6 • 25%
7 or more • 25%
Less than 100 • 25%
100-500 • 25%
501-1000 • 25%
More than 1000 • 25%
0-2 • 25%
3-4 • 25%
5-6 • 25%
Trial not completed • 25%
Less than 50 • 25%
50 to 100 • 25%
101 to 200 • 25%
More than 200 • 25%
Less than 10 • 25%
10 to 50 • 25%
51 to 100 • 25%
More than 100 • 25%
Yes • 50%
No • 50%
Less than 10 • 25%
10 to 50 • 25%
51 to 100 • 25%
More than 100 • 25%
1-5 patients • 25%
6-10 patients • 25%
11-20 patients • 25%
More than 20 patients • 25%
1-5 patients • 25%
6-10 patients • 25%
11-20 patients • 25%
More than 20 patients • 25%
Less than 10 • 25%
10 to 20 • 25%
21 to 30 • 25%
More than 30 • 25%
Yes • 50%
No • 50%
0-4 • 25%
5-9 • 25%
10-14 • 25%
15 or more • 25%