Skip to content

VAE and STCN with NMF for single-channel speech enhancement

License

Notifications You must be signed in to change notification settings

julius-richter/stcn-nmf

 
 

Repository files navigation

VAE and STCN implementations for single-channel speech enhancement

This repository contains the non-sequential VAE and STCN speech models and the NMF noise model for single-channel speech enhancement.

Whenever you use this code for any experiments and/or publications you need to cite our original paper [1].

[1] Julius Richter, Guillaume Carbajal, Timo Gerkmann, "Speech Enhancement with Stochastic Temporal Convolutional Networks", Proc. Interspeech 2020, DOI: 10.21437/Interspeech.2020-2588.

About

VAE and STCN with NMF for single-channel speech enhancement

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%