Skip to content

Decoding of the speech envelope from EEG using the VLAAI deep neural network. (PyTorch Implementation)

Notifications You must be signed in to change notification settings

carankt/vlaai-pytorch

Repository files navigation

VLAAI-pytorch

Decoding of the speech envelope using the VLAAI deep neural network. (Unofficial) PyTorch implementation.

=============================================================================

The vlaai network

This repository contains a pre-trained subject-independent model that can decode the speech envelope from EEG signals. The model was presented in the paper: Decoding of the speech envelope using the VLAAI deep neural network

by Bernd Accou, Jonas Vanthornhout, Hugo Van hamme, and Tom Francart.

This repository contains an unofficial PyTorch implementation of the VLAAI network.

Logs and results

Pre-trained model versions (using the preprocessing and dataset ( single-speaker stories dataset, 85 subjects that listened to 1 hour and 46 minutes on average for a total of 144 hours of EEG data) in the paper) are available in the pretrained_models folder.

Train Loss Valid Loss Correlation Metric

Performance Comparison with the original TensorFlow implementation on the DTU test set

Comparison

Original TensorFlow implementation: Here

About

Decoding of the speech envelope from EEG using the VLAAI deep neural network. (PyTorch Implementation)

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published