.png){kind=icon}
.png){kind=icon}
Return
Decoding inner speech via frequency-specific cortical EEG representations
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ipm.2026.104676.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Neural decoding of inner speech provides a crucial pathway for silent communication and cognitive state recognition. However, existing circular brain electrical activity mapping (BEAM)-based decoding methods suffer from the problem that edge distortion and information loss easily occur, and they are mismatched with the input structure of convolutional networks, ultimately limiting decoding accuracy. To overcome this problem, this paper first proposed a frequency-specific rectangular BEAM sequence construction method that employed an adaptive variation function to generate high-fidelity EEG sequences across different frequency bands, preserving cortical spatial correlations while perfectly matching the rectangular input structure of convolutional networks. Then, based on the continuous temporal and multi-frequency features of rectangular BEAM maps, 3D continuous frequency-spatial and temporal-spatial dynamic representation modules, respectively, were constructed. Finally, a dual-branch 3D convolutional network was designed to achieve joint decoding of inner speech brain activity. The manuscript reorganized the publicly available InnerSpeech dataset, involving 10 subjects, 3 task modalities, and 4 categories, with the first 10 trials selected for each condition. In total, 1200 samples were used to evaluate the proposed model’s ability to accurately classify inner speech. Experimental results showed that the proposed method outperformed the baseline model EEGNet, achieving accuracies of 61.79%, 62.67%, and 53.25% in the Inner, Pron, and Vis classification tasks, respectively, while also providing new insights into the mechanisms of frequency–task coupling and the development of high-precision brain–computer interfaces.
Keywords:
inner speech decoding
cortical EEG representations
frequency-specific
3D convolutional network
brain-computer interface
Journal
I
IF:
6.9
Papers:
332
Citations:
0