PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."
-
Updated
Aug 19, 2023 - Python
PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."
The official repo of NBC & SpatialNet for multichannel speech separation, denoising, and dereverberation
Ablation study of local spectral attention (LSA) for full-band speech enhancement (SE)
We design a spectral compression mapping (SCM) for full-band speech enhancement, and propose a two-stage stream named MHA-DPCRN
Band Structure and Density of States computation of the Brillouin Zone.
Add a description, image, and links to the full-band topic page so that developers can more easily learn about it.
To associate your repository with the full-band topic, visit your repo's landing page and select "manage topics."