mlsanityData to 14 Oct 2026

Dynamic nsNet2: Efficient Deep Noise Suppression with Early Exiting

arXiv 2308.16678 ↗First posted 31 Aug 2023cs.SD cs.LG eess.AScited by 7

Not on the map. Why?

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.

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

14 of 21 references.

References · 14

  1. 2021Dynamic Neural Networks: A Surveycited by 408
  2. 2020BERT Loses Patience: Fast and Robust Inference with Early Exitcited by 273
  3. 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 241
  4. 2020The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Resultscited by 133
  5. 2021Adaptive Inference through Early-Exit Networks: Design, Challenges and Directionscited by 75
  6. 2020Why should we add early exits to neural networks?cited by 70
  7. 2019Improved Techniques for Training Adaptive Deep Networkscited by 66
  8. 2017FreezeOut: Accelerate Training by Progressively Freezing Layerscited by 54
  9. 2020TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aidscited by 42
  10. 2021Zero Time Waste: Recycling Predictions in Early Exit Neural Networkscited by 39
  11. 2021Towards efficient models for real-time deep noise suppressioncited by 29
  12. 2020Data augmentation and loss normalization for deep noise suppressioncited by 23
2 more
  1. 2018Exploring Tradeoffs in Models for Low-latency Speech Enhancementcited by 8
  2. 2022Accelerating RNN-based Speech Enhancement on a Multi-Core MCU with Mixed FP16-INT8 Post-Training Quantizationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 2.

7 papers.

  1. 2024Scalable Speech Enhancement with Dynamic Channel Pruningcited by 5
  2. 2025Adaptive Slimming for Scalable and Efficient Speech Enhancementcited by 4
  3. 2024Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation Mapscited by 2
  4. 2025Knowing When to Quit: Probabilistic Early Exits for Speech Separationcited by 2
  5. 2025Hardware-Algorithm Co-Optimization of Early-Exit Neural Networks for Multi-Core Edge Acceleratorscited by 0
  6. 2026Performance and Complexity Trade-off Optimization of Speech Models During Trainingcited by 0
  7. 2026Does per-frame early exit pay? A compute-matched study of dynamic depth for on-device speech enhancementcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Performance optimizations on deep noise suppression models
  2. 2022Binary Early-Exit Network for Adaptive Inference on Low-Resource Devices
  3. 2023ABC-KD: Attention-Based-Compression Knowledge Distillation for Deep Learning-Based Noise Suppression
  4. 2026Distillation-based Layer Dropping (DLD): Effective End-to-end Framework for Dynamic Speech Networks
  5. 2023Sensitivity-Aware Finetuning for Accuracy Recovery on Deep Learning Hardware
  6. 2022Predictive Exit: Prediction of Fine-Grained Early Exits for Computation- and Energy-Efficient Inference
  7. 2025On Hardening DNNs against Noisy Computations
  8. 2021Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices