Dynamic nsNet2: Efficient Deep Noise Suppression with Early Exiting

Riccardo Miccini, Alaa Zniber, Clément Laroche, Tobias Piechowiak, Martin Schoeberl +4 more
8/31/2023
cs.SDcs.LGeess.AS

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

FREE-Merging: Fourier Transform for Efficient Model Merging

82% match2024

Computation-efficient Deep Learning for Computer Vision: A Survey

82% match2023

Pruning Early Exit Networks

82% match2022

DSD$^2$: Can We Dodge Sparse Double Descent and Compress the Neural Network Worry-Free?

82% match1 repo32023

Knowing When to Quit: Probabilistic Early Exits for Speech Separation

82% match2025

The mechanism underlying successful deep learning

81% match2023

Cite this paper

@article{miccini2023dynamic,
  title  = {Dynamic nsNet2: Efficient Deep Noise Suppression with Early Exiting},
  author = {Riccardo Miccini and Alaa Zniber and Clément Laroche and Tobias Piechowiak and Martin Schoeberl and Luca Pezzarossa and Ouassim Karrakchou and Jens Sparsø and Mounir Ghogho},
  year   = {2023},
  eprint = {2308.16678},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.16678v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.16678.svg)](https://codeofpaper.com/paper/2308.16678)

Discussion