Trainging, inference, and testing of the SAC speech codec model.
-
Updated
Nov 1, 2025 - Python
#
speech-reconstruction
Here are 4 public repositories matching this topic...
deep-neural-networks computer-vision deep-learning autoencoder speech-reconstruction auditory-spectrograms
-
Updated
Oct 8, 2018 - Jupyter Notebook
In this work we propose two postprocessing approaches applying convolutional neural networks (CNNs) either in the time domain or the cepstral domain to enhance the coded speech without any modification of the codecs. The time domain approach follows an end-to-end fashion, while the cepstral domain approach uses analysis-synthesis with cepstral d…
keras cnn generative-adversarial-network gan post-processing mfcc speech-processing wasserstein-gan speech-enhancement speech-reconstruction 1d-convolution
-
Updated
Mar 8, 2020 - Python
Speech reconstruction and compression with autoencoders
-
Updated
Feb 22, 2022 - Python
Improve this page
Add a description, image, and links to the speech-reconstruction topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the speech-reconstruction topic, visit your repo's landing page and select "manage topics."