Decoding High-level Imagined Speech using Attention-based Deep Neural Networks
This work addresses the challenge of improving brain-computer interface communication for users by enhancing decoding of imagined speech, though it appears incremental as it modifies a previous model.
The researchers tackled the problem of decoding imagined speech from EEG signals, achieving an average accuracy of 0.5648 for classifying four words across ten subjects, demonstrating feasibility with robust performance.
Brain-computer interface (BCI) is the technology that enables the communication between humans and devices by reflecting status and intentions of humans. When conducting imagined speech, the users imagine the pronunciation as if actually speaking. In the case of decoding imagined speech-based EEG signals, complex task can be conducted more intuitively, but decoding performance is lower than that of other BCI paradigms. We modified our previous model for decoding imagined speech-based EEG signals. Ten subjects participated in the experiment. The average accuracy of our proposed method was 0.5648 for classifying four words. In other words, our proposed method has significant strength in learning local features. Hence, we demonstrated the feasibility of decoding imagined speech-based EEG signals with robust performance.