# Dynamic Slimmable Networks for Efficient Speech Separation

arXiv: https://arxiv.org/abs/2507.06179 · HTML: https://mlsanity.com/paper/2507.06179/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2025.

## Built on by (most cited first, 3 of 3)

- [From Diet to Free Lunch: Estimating Auxiliary Signal Properties using Dynamic Pruning Masks in Speech Enhancement Networks](https://mlsanity.com/paper/2602.10666/) (2026)
- [Slimmable NAM: Neural Amp Models with adjustable runtime computational cost](https://mlsanity.com/paper/2511.07470/) (2025)
- [Does per-frame early exit pay? A compute-matched study of dynamic depth for on-device speech enhancement](https://mlsanity.com/paper/2609.29867/) (2026)

## Abstract (arXiv)

Recent progress in speech separation has been largely driven by advances in deep neural networks, yet their high computational and memory requirements hinder deployment on resource-constrained devices. A significant inefficiency in conventional systems arises from using static network architectures that maintain constant computational complexity across all input segments, regardless of their characteristics. This approach is sub-optimal for simpler segments that do not require intensive processing, such as silence or non-overlapping speech. To address this limitation, we propose a dynamic slimmable network (DSN) for speech separation that adaptively adjusts its computational complexity based on the input signal. The DSN combines a slimmable network, which can operate at different network widths, with a lightweight gating module that dynamically determines the required width by analyzing the local input characteristics. To balance performance and efficiency, we introduce a signal-dependent complexity loss that penalizes unnecessary computation based on segmental reconstruction error. Experiments on clean and noisy two-speaker mixtures from the WSJ0-2mix and WHAM! datasets show that the DSN achieves a better performance-efficiency trade-off than individually trained static networks of different sizes.