Single-Channel Speech Enhancement with Deep Complex U-Networks and Probabilistic Latent Space Models.

Eike Jannik Nustede Jörn Anemüller

Published in: ICASSP (2023)

Keyphrases

single channel
speech enhancement
multi channel
probabilistic model
noisy environments
generative model
latent space
noise reduction
signal to noise ratio
bayesian framework
latent variables
vocal tract
image processing
prior information
speech recognition
language model
feature vectors