# SlimDiffuSE: Towards Efficient Diffusion-Based Speech Enhancement using Slimmable Networks

arXiv: https://arxiv.org/abs/2608.21188 · HTML: https://mlsanity.com/paper/2608.21188/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 25 of its 32 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 25 of 25)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Improved Techniques for Training Score-Based Generative Models](https://mlsanity.com/paper/2006.09011/) (2020)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022)
- [SEGAN: Speech Enhancement Generative Adversarial Network](https://mlsanity.com/paper/1703.09452/) (2017)
- [DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement](https://mlsanity.com/paper/2008.00264/) (2020)
- [FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis](https://mlsanity.com/paper/2204.09934/) (2022)
- [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results](https://mlsanity.com/paper/2005.13981/) (2020)
- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2212.11851/) (2022)
- [Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain](https://mlsanity.com/paper/2203.17004/) (2022)
- [A Recurrent Variational Autoencoder for Speech Enhancement](https://mlsanity.com/paper/1910.10942/) (2019)
- [Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restoration](https://mlsanity.com/paper/2211.02397/) (2022)
- [FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement](https://mlsanity.com/paper/2203.12188/) (2022)
- [DeepFilterNet2: Towards Real-Time Speech Enhancement on Embedded Devices for Full-Band Audio](https://mlsanity.com/paper/2205.05474/) (2022)
- [Denoising Diffusion Step-aware Models](https://mlsanity.com/paper/2310.03337/) (2023)
- [Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer](https://mlsanity.com/paper/2010.12180/) (2020)
- [Real-time Denoising and Dereverberation with Tiny Recurrent U-Net](https://mlsanity.com/paper/2102.03207/) (2021)
- [Ultra Low Complexity Deep Learning Based Noise Suppression](https://mlsanity.com/paper/2312.08132/) (2023)
- [GAN-Based Speech Enhancement for Low SNR Using Latent Feature Conditioning](https://mlsanity.com/paper/2410.13599/) (2024)
- [Comparative Analysis Of Discriminative Deep Learning-Based Noise Reduction Methods In Low SNR Scenarios](https://mlsanity.com/paper/2408.14582/) (2024)
- [A Hybrid Approach for Low-Complexity Joint Acoustic Echo and Noise Reduction](https://mlsanity.com/paper/2408.15746/) (2024)
- [Leveraging Discriminative Latent Representations for Conditioning GAN-Based Speech Enhancement](https://mlsanity.com/paper/2508.20859/) (2025)

## Abstract (arXiv)

Diffusion-based models are emerging in the speech enhancement domain and are achieving state-of-the-art performance across various benchmark datasets. A major downside of diffusion models is that data generation requires many evaluations of a typically large neural network, which results in high overall complexity. In this work, we propose a slimmable diffusion model that employs adaptive network widths throughout the data generation process to reduce computational cost. By using a greedy search algorithm to optimize the network width schedule, our method achieves performance comparable to baseline diffusion models with significantly reduced computational complexity. Notably, our approach reduces the computational complexity by up to 87.5% without a significant drop in objective metrics, such as perceptual evaluation of speech quality (PESQ) and SI-SDR.