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.
Decoding speech perception from non-invasive brain recordings.Nature Machine Intelligence, 5(10):1097–1107, Oct 2023
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
PNA decomposes MEG recordings via ICA, isolates artifact components using EOG/ECG references, and re-injects scaled artifacts into clean data to train decoders that are invariant to physiological noise, improving imagined-digit classification by 4.7 percentage points with EEGNet.
The paper introduces a time-resolved neural encoder combining Whisper embeddings with recurrent temporal modeling and soft attention to predict ECoG responses, finding strongest alignment in intermediate layers and anatomically coherent phoneme organization in electrodes.
Separating acoustic and expectation ANN representations as teacher targets improves EEG music identification beyond baselines and seed ensembles.
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.
-
Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech
PNA decomposes MEG recordings via ICA, isolates artifact components using EOG/ECG references, and re-injects scaled artifacts into clean data to train decoders that are invariant to physiological noise, improving imagined-digit classification by 4.7 percentage points with EEGNet.
-
Mapping Whisper Representations to Human ECoG Responses with Interpretable Time-Resolved Neural Encoding
The paper introduces a time-resolved neural encoder combining Whisper embeddings with recurrent temporal modeling and soft attention to predict ECoG responses, finding strongest alignment in intermediate layers and anatomically coherent phoneme organization in electrodes.
-
Expectation and Acoustic Neural Network Representations Enhance Music Identification from Brain Activity
Separating acoustic and expectation ANN representations as teacher targets improves EEG music identification beyond baselines and seed ensembles.