轻量级Mamba模型实现高效语音去噪，参数仅442K却媲美大模型。
CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel Pruning
- 用Mamba替代传统注意力和LSTM，提升去噪效率
- 通道剪枝使模型缩小8倍，仍保持95.1%的语音可懂度
- 适合实时音频处理，参数少、算力低、效果佳
本文提出CleanUMamba，一种面向实时因果语音去噪的时域神经网络，直接作用于原始波形。该模型采用U-Net编码器-解码器结构，在瓶颈层引入Mamba状态空间模型，取代传统的自注意力与LSTM机制，实现优异去噪性能且内存恒定，支持流式处理。为提升效率，应用结构化通道剪枝，模型规模减少8倍，未损失音频质量。在Interspeech 2020深度降噪挑战中表现突出：参数仅442K，计算量468M MACs，PESQ达2.42，STOI为95.1%，在实时性方面达到或超越更大模型水平。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。