Sudo rm -rf: Efficient Networks for Universal Audio Source Separation

Efthymios Tzinis, Zhepei Wang, Paris Smaragdis
7/14/2020
eess.AScs.CLcs.LG

Official code: etzinis/sudo_rm_rf (339 stars, MIT, last commit 2023-07-06).

Abstract

In this paper, we present an efficient neural network for end-to-end general purpose audio source separation. Specifically, the backbone structure of this convolutional network is the SUccessive DOwnsampling and Resampling of Multi-Resolution Features (SuDoRMRF) as well as their aggregation which is performed through simple one-dimensional convolutions. In this way, we are able to obtain high quality audio source separation with limited number of floating point operations, memory requirements, number of parameters and latency. Our experiments on both speech and environmental sound separation datasets show that SuDoRMRF performs comparably and even surpasses various state-of-the-art approaches with significantly higher computational resource requirements.

View on arXivView PDF

Code Implementations(1)

etzinis/sudo_rm_rfOfficial100%
MIT

Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-Resolution Features which enables a more efficient way of separating sources from mixtures.

33937Shell, PythonJul 12, 20203 years agoMIT
audiodeep-learningspeechspeech-separation

Similar Papers

Compute and memory efficient universal sound source separation

92% match1 repo3392021

A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation

86% match1 repo1632023

Sampling-Frequency-Independent Universal Sound Separation

83% match2023

Learning to Separate Voices by Spatial Regions

83% match2022

Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation

82% match1 repo3382018

Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction

82% match1 repo832017

Cite this paper

@article{tzinis2020sudo,
  title  = {Sudo rm -rf: Efficient Networks for Universal Audio Source Separation},
  author = {Efthymios Tzinis and Zhepei Wang and Paris Smaragdis},
  year   = {2020},
  eprint = {2007.06833},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2007.06833}
}

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/2007.06833.svg)](https://codeofpaper.com/paper/2007.06833)

Discussion