mlsanityData to 7 Oct 2026

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

arXiv 2007.06833 ↗First posted 14 Jul 2020eess.AS cs.CL cs.LGcited by 50

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 9; 2023: 9; 2024: 15; 2025: 3; 2026: 4.

50 papers.

Sort:

By area:

  1. 2024Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separationcited by 45
  2. 2022An efficient encoder-decoder architecture with top-down attention for speech separationcited by 38
  3. 2025SepPrune: Structured Pruning for Efficient Deep Speech Separationcited by 31
  4. 2021Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Datacited by 27
  5. 2023MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentionscited by 27
  6. 2022RemixIT: Continual self-training of speech enhancement models via bootstrapped remixingcited by 20
  7. 2024Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealingcited by 12
  8. 2022Resource-Efficient Separation Transformercited by 11
  9. 2024TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separationcited by 10
  10. 2022An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuitscited by 9
  11. 2023Subnetwork-to-go: Elastic Neural Network with Dynamic Training and Customizable Inferencecited by 9
  12. 2021Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Datacited by 8
38 more
  1. 2021Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Acceleratorscited by 8
  2. 2021Hybrid Neural Networks for On-device Directional Hearingcited by 8
  3. 2021REAL-M: Towards Speech Separation on Real Mixturescited by 7
  4. 2022MixCycle: Unsupervised Speech Separation via Cyclic Mixture Permutation Invariant Trainingcited by 7
  5. 2021Continual self-training with bootstrapped remixing for speech enhancementcited by 6
  6. 2022Exploiting Temporal Structures of Cyclostationary Signals for Data-Driven Single-Channel Source Separationcited by 6
  7. 2023A Neural State-Space Model Approach to Efficient Speech Separationcited by 6
  8. 2023Spatial LibriSpeech: An Augmented Dataset for Spatial Audio Learningcited by 6
  9. 2024Neural Blind Source Separation and Diarization for Distant Speech Recognitioncited by 6
  10. 2024RF Challenge: The Data-Driven Radio Frequency Signal Separation Challengecited by 5
  11. 2024SepMamba: State-space models for speaker separation using Mambacited by 5
  12. 2021Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domaincited by 4
  13. 2022Exploring Self-Attention Mechanisms for Speech Separationcited by 4
  14. 2024SonicSim: A customizable simulation platform for speech processing in moving sound source scenarioscited by 4
  15. 2025A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy Referencescited by 4
  16. 2021BLOOM-Net: Blockwise Optimization for Masking Networks Toward Scalable and Efficient Speech Enhancementcited by 3
  17. 2022Deep neural network techniques for monaural speech enhancement: state of the art analysiscited by 3
  18. 2023On Neural Architectures for Deep Learning-based Source Separation of Co-Channel OFDM Signalscited by 3
  19. 2021Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanismcited by 2
  20. 2022Fine-grained Noise Control for Multispeaker Speech Synthesiscited by 2
  21. 2023An Efficient Speech Separation Network Based on Recurrent Fusion Dilated Convolution and Channel Attentioncited by 2
  22. 2023Neural Fast Full-Rank Spatial Covariance Analysis for Blind Source Separationcited by 2
  23. 2024Online speaker diarization of meetings guided by speech separationcited by 2
  24. 2024Sound Source Separation Using Latent Variational Block-Wise Disentanglementcited by 2
  25. 2024U-Mamba-Net: A highly efficient Mamba-based U-net style network for noisy and reverberant speech separationcited by 2
  26. 2025Knowing When to Quit: Probabilistic Early Exits for Speech Separationcited by 2
  27. 2026The Radio-Frequency Transformer for Signal Separationcited by 2
  28. 2021A Time-domain Real-valued Generalized Wiener Filter for Multi-channel Neural Separation Systemscited by 1
  29. 2024TDFNet: An Efficient Audio-Visual Speech Separation Model with Top-down Fusioncited by 1
  30. 2024SPMamba: State-space model is all you need in speech separationcited by 1
  31. 2026Omni-directional attention mechanism based on Mamba for speech separationcited by 1
  32. 2026Difference-Driven Gating: Adaptive Feature Fusion for U-Net Decodercited by 1
  33. 2023Scaling strategies for on-device low-complexity source separation with Conv-Tasnetcited by 0
  34. 2023Improving Label Assignments Learning by Dynamic Sample Dropout Combined with Layer-wise Optimization in Speech Separationcited by 0
  35. 2024Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challengecited by 0
  36. 2024Effects of Dataset Sampling Rate for Noise Cancellation through Deep Learningcited by 0
  37. 2024Extract and Diffuse: Latent Integration for Improved Diffusion-based Speech and Vocal Enhancementcited by 0
  38. 2026TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separationcited by 0