<ul><li>U-Mamba-Net is a lightweight Mamba-based U-style model for speech separation in complex environments.</li><li>The model aims to address the increasing size and computational load of existing speech separation models.</li><li>Mamba is a state space sequence model that incorporates feature selection capabilities.</li><li>U-Mamba-Net achieves improved performance with low computational cost according to the results on Libri2mix.</li></ul>

U-Mamba-Net: A highly efficient Mamba-based U-net style network for noisy and reverberant speech separation

Discover more