Section: New Software and Platforms

SE-VAE-NMF

Keywords: Audio signal processing - Speech processing - Deep learning - Neural networks

Functional Description: This software provides an iterative algorithm for enhancing a speech signal in a noisy monophonic recording. The algorithm is detailed in the following paper: "A variance modeling framework based on variational autoencoders for speech enhancement" Simon Leglaive, Laurent Girin, Radu Horaud Proc. of the IEEE International Workshop on Machine Learning for Signal Processing (MLSP), Aalborg, Denmark, September 2018

• Contact: Simon Leglaive

• Publication: hal-01832826v1