Richárd Csáky

This paper investigates decoding inner speech using EEG and MEG, finding that silent reading can be decoded with moderate accuracy while inner speech tasks perform at chance level.

This paper demonstrates that wearable magnetometers can achieve high accuracy in silent speech recognition, outperforming existing methods and showing generalizability across users.

This paper develops a magnetomyography-based system for gesture recognition, achieving high accuracy and cross-participant performance, suggesting its potential as a generalizable alternative to sEMG.

This paper investigates magnetomyography (MMG) by simultaneously recording it with surface electromyography (sEMG) during muscle contractions, finding linear correlation with contraction intensity and differences in frequency content.

This paper introduces a multiclass full-epoch decoding approach for M/EEG data that improves accuracy over sliding window methods while enabling interpretation of spatiotemporal features.