Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Imagined Speech and Visual Imagery as Intuitive Paradigms for Brain-Computer Interfaces

Seo-Hyun Lee, Ji-Ha Park, Deok-Seon Kim

TL;DR

This paper investigates non-invasive BCIs by comparing imagined speech and visual imagery using $PLV$-based functional connectivity in EEG across four frequency bands and seven cortical regions in 16 participants. It shows that visual imagery engages visual/spatial networks with higher PLV, while imagined speech produces consistent synchronization in language-related regions, indicating distinct neural substrates. The results underscore the need for personalized calibration and point to hybrid BCIs that combine both paradigms to improve reliability for users with speech impairments. These insights inform design of intuitive, language-oriented and visually-guided BCIs with potential for broader real-world adoption.

Abstract

Brain-computer interfaces (BCIs) have shown promise in enabling communication for individuals with motor impairments. Recent advancements like brain-to-speech technology aim to reconstruct speech from neural activity. However, decoding communication-related paradigms, such as imagined speech and visual imagery, using non-invasive techniques remains challenging. This study analyzes brain dynamics in these two paradigms by examining neural synchronization and functional connectivity through phase-locking values (PLV) in EEG data from 16 participants. Results show that visual imagery produces higher PLV values in visual cortex, engaging spatial networks, while imagined speech demonstrates consistent synchronization, primarily engaging language-related regions. These findings suggest that imagined speech is suitable for language-driven BCI applications, while visual imagery can complement BCI systems for users with speech impairments. Personalized calibration is crucial for optimizing BCI performance.

Imagined Speech and Visual Imagery as Intuitive Paradigms for Brain-Computer Interfaces

TL;DR

This paper investigates non-invasive BCIs by comparing imagined speech and visual imagery using -based functional connectivity in EEG across four frequency bands and seven cortical regions in 16 participants. It shows that visual imagery engages visual/spatial networks with higher PLV, while imagined speech produces consistent synchronization in language-related regions, indicating distinct neural substrates. The results underscore the need for personalized calibration and point to hybrid BCIs that combine both paradigms to improve reliability for users with speech impairments. These insights inform design of intuitive, language-oriented and visually-guided BCIs with potential for broader real-world adoption.

Abstract

Brain-computer interfaces (BCIs) have shown promise in enabling communication for individuals with motor impairments. Recent advancements like brain-to-speech technology aim to reconstruct speech from neural activity. However, decoding communication-related paradigms, such as imagined speech and visual imagery, using non-invasive techniques remains challenging. This study analyzes brain dynamics in these two paradigms by examining neural synchronization and functional connectivity through phase-locking values (PLV) in EEG data from 16 participants. Results show that visual imagery produces higher PLV values in visual cortex, engaging spatial networks, while imagined speech demonstrates consistent synchronization, primarily engaging language-related regions. These findings suggest that imagined speech is suitable for language-driven BCI applications, while visual imagery can complement BCI systems for users with speech impairments. Personalized calibration is crucial for optimizing BCI performance.

Paper Structure

This paper contains 10 sections, 2 equations, 1 figure, 3 tables.

Table of Contents

  1. INTRODUCTION
  2. METHODS
  3. Dataset Description
  4. Brain Decoding and Connectivity Analysis
  5. RESULTS AND DISCUSSION
  6. PLV Analysis
  7. Comparison of Paradigms
  8. Brain Region Analysis
  9. Implications for BCI Applications
  10. CONCLUSION

Figures (1)

  • Figure 1: The overall experimental paradigm was designed to investigate the cognitive processes related to (a) imagined speech and (b) visual imagery through specific task performance while recording brain activity. The experimental setup for collecting EEG signals involved placing a EEG cap on participants in a quiet environment to ensure accurate data acquisition.