A rigorous leave-one-subject-out benchmark on public auditory EEG data shows five-vowel decoding accuracy of 25.5 percent (chance 20 percent) using differential entropy features and LightGBM, with vowel information present but weak and localized to early auditory transients.
Classi- fication of covariance matrices using a Riemannian-based kernel for BCI applications
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
How Well Can We Decode Vowels from Auditory EEG -- A Rigorous Cross-Subject Benchmark with Honest Assessment
A rigorous leave-one-subject-out benchmark on public auditory EEG data shows five-vowel decoding accuracy of 25.5 percent (chance 20 percent) using differential entropy features and LightGBM, with vowel information present but weak and localized to early auditory transients.