REVIEW 3 cited by
Scaling Law in Neural Data: Non-Invasive Speech Decoding with 175 Hours of EEG Data
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Brain-computer interfaces (BCIs) hold great potential for aiding individuals with speech impairments. Utilizing electroencephalography (EEG) to decode speech is particularly promising due to its non-invasive nature. However, recordings are typically short, and the high variability in EEG data has led researchers to focus on classification tasks with a few dozen classes. To assess its practical applicability for speech neuroprostheses, we investigate the relationship between the size of EEG data and decoding accuracy in the open vocabulary setting. We collected extensive EEG data from a single participant (175 hours) and conducted zero-shot speech segment classification using self-supervised representation learning. The model trained on the entire dataset achieved a top-1 accuracy of 48\% and a top-10 accuracy of 76\%, while mitigating the effects of myopotential artifacts. Conversely, when the data was limited to the typical amount used in practice ($\sim$10 hours), the top-1 accuracy dropped to 2.5\%, revealing a significant scaling effect. Additionally, as the amount of training data increased, the EEG latent representation progressively exhibited clearer temporal structures of spoken phrases. This indicates that the decoder can recognize speech segments in a data-driven manner without explicit measurements of word recognition. This research marks a significant step towards the practical realization of EEG-based speech BCIs.
Forward citations
Cited by 3 Pith papers
-
SoniSpeech: A Large-Scale Open-Vocabulary Tri-Modal Dataset for Wearable Silent Speech Interfaces
SoniSpeech, the first open-vocabulary trimodal silent speech dataset from acoustic-sensing eyewear, achieves 26.3% WER in a CTC ResNet baseline.
-
A Silent Speech Decoding System from EEG and EMG with Heterogenous Electrode Configurations
A multi-task neural net pre-trained on 220 hours of heterogeneous EEG/EMG decodes silent speech words at 95.3% accuracy in healthy users and 54.5% in one patient, beating single-subject baselines.
-
A Dataset Generation Scheme Based on Video2EEG-SPGN-Diffusion for SEED-VD
Claims a video-to-EEG generative framework and a 1000-sample public dataset, but the experimental sections report mutually contradictory quality scores, and neither code nor dataset is provided.
Discussion (0). Continue with ORCID to comment.