EEG-Based Imagined Speech Decoding Using a Hybrid CNN-SNN Architecture

2026-07-04

AI Summary

This study addresses the challenges of non-stationarity, low signal amplitude, and high inter-subject variability in electroencephalography (EEG)-based imagined speech decoding by proposing a hybrid CNN-SNN architecture. The framework first employs a convolutional neural network (CNN) to extract temporal features from EEG signals, followed by a spiking neural network (SNN) that performs brain-inspired temporal dynamic classification. This work represents the first application of SNNs to imagined speech decoding, establishing a neuromorphic decoding pipeline that achieves both high performance and biological plausibility. Evaluated on the 2020 BCI Competition III benchmark dataset, the proposed model attains an accuracy of 80.13%, significantly outperforming the previous state-of-the-art method (70.19%) and demonstrating the efficacy of spike-timing-based encoding for imagined speech decoding.

Abstract

Imagined speech decoding using EEG signals has emerged as a promising frontier in brain-computer interface (BCI) research, particularly to restore communication for individuals with severe speech impairments. However, decoding imagined speech remains a complex task due to the non-stationary, low-amplitude, and highly variable nature of EEG signals. Existing methods often rely on classical machine learning or deep learning models that fail to exploit spike-based temporal dynamics or event-driven firing mechanisms of biological neurons, which are naturally modeled by spiking neural networks (SNNs). In this study, we propose a hybrid decoding pipeline that extracts temporal representations using convolutional neural networks (CNNs) followed by biologically inspired temporal classification via SNNs. To our knowledge, this is the first study to integrate SNNs into EEG-based imagined speech decoding. Experimental results show that the proposed CNN-SNN architecture achieves an accuracy of 80.13% on the 2020 BCI Competition III benchmark, surpassing existing methods reported in the literature (up to 70.19%) under comparable evaluation settings. These findings demonstrate the effectiveness of spike-based temporal decoding for imagined speech, highlighting the promise of biologically grounded pipelines for next generation neuromorphic BCI applications.

Problem

• imagined speech
• EEG decoding
• brain-computer interface
• non-stationary signals
• speech impairment

Innovation

• spiking neural networks
• imagined speech decoding
• hybrid CNN-SNN
• EEG-based BCI
• temporal dynamics