# Learning Subject-Invariant Representations from Speech-Evoked EEG Using Variational Autoencoders

arXiv: https://arxiv.org/abs/2207.00323 · HTML: https://mlsanity.com/paper/2207.00323/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 1 Jul 2022.

## Builds on (most cited first, 6 of 6)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data](https://mlsanity.com/paper/1709.07902/) (2017)
- [An LSTM Based Architecture to Relate Speech Stimulus to EEG](https://mlsanity.com/paper/2002.10988/) (2020)
- [Adversarial Deep Learning in EEG Biometrics](https://mlsanity.com/paper/1903.11673/) (2019)
- [Scalable Factorized Hierarchical Variational Autoencoder Training](https://mlsanity.com/paper/1804.03201/) (2018)

## Built on by (most cited first, 5 of 5)

- [CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal Conversion](https://mlsanity.com/paper/2311.07788/) (2023)
- [Variational Autoencoder Learns Better Feature Representations for EEG-based Obesity Classification](https://mlsanity.com/paper/2302.00789/) (2023)
- [Decoding Linguistic Representations of Human Brain](https://mlsanity.com/paper/2407.20622/) (2024)
- [Subject Representation Learning from EEG using Graph Convolutional Variational Autoencoders](https://mlsanity.com/paper/2501.16626/) (2025)
- [Continuous Indeterminate Probability Neural Network](https://mlsanity.com/paper/2303.12964/) (2023)

## Abstract (arXiv)

The electroencephalogram (EEG) is a powerful method to understand how the brain processes speech. Linear models have recently been replaced for this purpose with deep neural networks and yield promising results. In related EEG classification fields, it is shown that explicitly modeling subject-invariant features improves generalization of models across subjects and benefits classification accuracy. In this work, we adapt factorized hierarchical variational autoencoders to exploit parallel EEG recordings of the same stimuli. We model EEG into two disentangled latent spaces. Subject accuracy reaches 98.96% and 1.60% on respectively the subject and content latent space, whereas binary content classification experiments reach an accuracy of 51.51% and 62.91% on respectively the subject and content latent space.