Constrained Variational Autoencoder for improving EEG based Speech Recognition Systems
This work addresses the challenge of enhancing EEG-based speech recognition systems, which is incremental as it builds on existing VAE methods with a new constrained loss function.
The authors tackled the problem of improving EEG-based speech recognition by introducing a constrained VAE model that generates more meaningful EEG features, resulting in improved performance for both continuous and isolated speech recognition tasks, with demonstrated outperformance over a recent method as vocabulary size increases.
In this paper we introduce a recurrent neural network (RNN) based variational autoencoder (VAE) model with a new constrained loss function that can generate more meaningful electroencephalography (EEG) features from raw EEG features to improve the performance of EEG based speech recognition systems. We demonstrate that both continuous and isolated speech recognition systems trained and tested using EEG features generated from raw EEG features using our VAE model results in improved performance and we demonstrate our results for a limited English vocabulary consisting of 30 unique sentences for continuous speech recognition and for an English vocabulary consisting of 2 unique sentences for isolated speech recognition. We compare our method with another recently introduced method described by authors in [1] to improve the performance of EEG based continuous speech recognition systems and we demonstrate that our method outperforms their method as vocabulary size increases when trained and tested using the same data set. Even though we demonstrate results only for automatic speech recognition (ASR) experiments in this paper, the proposed VAE model with constrained loss function can be extended to a variety of other EEG based brain computer interface (BCI) applications.