# Dynamic nsNet2: Efficient Deep Noise Suppression with Early Exiting

arXiv: https://arxiv.org/abs/2308.16678 · HTML: https://mlsanity.com/paper/2308.16678/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 31 Aug 2023.

## Builds on (most cited first, 14 of 14)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [BERT Loses Patience: Fast and Robust Inference with Early Exit](https://mlsanity.com/paper/2006.04152/) (2020)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results](https://mlsanity.com/paper/2005.13981/) (2020)
- [Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions](https://mlsanity.com/paper/2106.05022/) (2021)
- [Why should we add early exits to neural networks?](https://mlsanity.com/paper/2004.12814/) (2020)
- [Improved Techniques for Training Adaptive Deep Networks](https://mlsanity.com/paper/1908.06294/) (2019)
- [FreezeOut: Accelerate Training by Progressively Freezing Layers](https://mlsanity.com/paper/1706.04983/) (2017)
- [TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids](https://mlsanity.com/paper/2005.11138/) (2020)
- [Zero Time Waste: Recycling Predictions in Early Exit Neural Networks](https://mlsanity.com/paper/2106.05409/) (2021)
- [Towards efficient models for real-time deep noise suppression](https://mlsanity.com/paper/2101.09249/) (2021)
- [Data augmentation and loss normalization for deep noise suppression](https://mlsanity.com/paper/2008.06412/) (2020)
- [Exploring Tradeoffs in Models for Low-latency Speech Enhancement](https://mlsanity.com/paper/1811.07030/) (2018)
- [Accelerating RNN-based Speech Enhancement on a Multi-Core MCU with Mixed FP16-INT8 Post-Training Quantization](https://mlsanity.com/paper/2210.07692/) (2022)

## Built on by (most cited first, 7 of 7)

- [Scalable Speech Enhancement with Dynamic Channel Pruning](https://mlsanity.com/paper/2412.17121/) (2024)
- [Adaptive Slimming for Scalable and Efficient Speech Enhancement](https://mlsanity.com/paper/2507.04879/) (2025)
- [Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation Maps](https://mlsanity.com/paper/2407.04578/) (2024)
- [Knowing When to Quit: Probabilistic Early Exits for Speech Separation](https://mlsanity.com/paper/2507.09768/) (2025)
- [Hardware-Algorithm Co-Optimization of Early-Exit Neural Networks for Multi-Core Edge Accelerators](https://mlsanity.com/paper/2512.04705/) (2025)
- [Performance and Complexity Trade-off Optimization of Speech Models During Training](https://mlsanity.com/paper/2601.13704/) (2026)
- [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)

Although deep learning has made strides in the field of deep noise suppression, leveraging deep architectures on resource-constrained devices still proved challenging. Therefore, we present an early-exiting model based on nsNet2 that provides several levels of accuracy and resource savings by halting computations at different stages. Moreover, we adapt the original architecture by splitting the information flow to take into account the injected dynamism. We show the trade-offs between performance and computational complexity based on established metrics.