CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel Pruning

Sjoerd Groot, Qinyu Chen, Jan C. van Gemert, Chang Gao
10/14/2024
cs.SDcs.AIcs.CV

Official code: lab-emi/CleanUMamba (27 stars, last commit 2025-06-12).

Abstract

This paper presents CleanUMamba, a time-domain neural network architecture designed for real-time causal audio denoising directly applied to raw waveforms. CleanUMamba leverages a U-Net encoder-decoder structure, incorporating the Mamba state-space model in the bottleneck layer. By replacing conventional self-attention and LSTM mechanisms with Mamba, our architecture offers superior denoising performance while maintaining a constant memory footprint, enabling streaming operation. To enhance efficiency, we applied structured channel pruning, achieving an 8X reduction in model size without compromising audio quality. Our model demonstrates strong results in the Interspeech 2020 Deep Noise Suppression challenge. Specifically, CleanUMamba achieves a PESQ score of 2.42 and STOI of 95.1% with only 442K parameters and 468M MACs, matching or outperforming larger models in real-time performance. Code will be available at: https://github.com/lab-emi/CleanUMamba

View on arXivView PDF

Code Implementations(1)

lab-emi/CleanUMambaOfficial100%

CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel Pruning [Official PyTorch implementation]

279PythonOct 13, 20241 years ago

Similar Papers

WaveLLDM: Design and Development of a Lightweight Latent Diffusion Model for Speech Enhancement and Restoration

86% match2025

ADNAC: Audio Denoiser using Neural Audio Codec

83% match2025

Effects of Dataset Sampling Rate for Noise Cancellation through Deep Learning

83% match2024

RT-LA-VocE: Real-Time Low-SNR Audio-Visual Speech Enhancement

82% match2024

IS${}^3$ : Generic Impulsive--Stationary Sound Separation in Acoustic Scenes using Deep Filtering

82% match1 repo62025

Classic Video Denoising in a Machine Learning World: Robust, Fast, and Controllable

82% match2026

Cite this paper

@article{groot2024cleanumamba,
  title  = {CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel Pruning},
  author = {Sjoerd Groot and Qinyu Chen and Jan C. van Gemert and Chang Gao},
  year   = {2024},
  eprint = {2410.11062},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.11062v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.11062.svg)](https://codeofpaper.com/paper/2410.11062)

Discussion