mlsanityData to 7 Oct 2026

Blind Restoration of Real-World Audio by 1D Operational GANs

arXiv 2212.14618 ↗First posted 30 Dec 2022cs.SD cs.LG eess.AScited by 3

Not on the map. Why?

Abstract (arXiv)

Objective: Despite numerous studies proposed for audio restoration in the literature, most of them focus on an isolated restoration problem such as denoising or dereverberation, ignoring other artifacts. Moreover, assuming a noisy or reverberant environment with limited number of fixed signal-to-distortion ratio (SDR) levels is a common practice. However, real-world audio is often corrupted by a blend of artifacts such as reverberation, sensor noise, and background audio mixture with varying types, severities, and duration. In this study, we propose a novel approach for blind restoration of real-world audio signals by Operational Generative Adversarial Networks (Op-GANs) with temporal and spectral objective metrics to enhance the quality of restored audio signal regardless of the type and severity of each artifact corrupting it. Methods: 1D Operational-GANs are used with generative neuron model optimized for blind restoration of any corrupted audio signal. Results: The proposed approach has been evaluated extensively over the benchmark TIMIT-RAR (speech) and GTZAN-RAR (non-speech) datasets corrupted with a random blend of artifacts each with a random severity to mimic real-world audio signals. Average SDR improvements of over 7.2 dB and 4.9 dB are achieved, respectively, which are substantial when compared with the baseline methods. Significance: This is a pioneer study in blind audio restoration with the unique capability of direct (time-domain) restoration of real-world audio whilst achieving an unprecedented level of performance for a wide SDR range and artifact types. Conclusion: 1D Op-GANs can achieve robust and computationally effective real-world audio restoration with significantly improved performance. The source codes and the generated real-world audio datasets are shared publicly with the research community in a dedicated GitHub repository1.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 31 of its 51 references that are in the map. First posted on arXiv 30 Dec 2022.

Builds on

31 of 51 references.

References · 31

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  4. 2014Conditional Generative Adversarial Netscited by 2,152
  5. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  6. 2016Least Squares Generative Adversarial Networkscited by 1,000
  7. 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 165
  8. 2021MetricGAN+: An Improved Version of MetricGAN for Speech Enhancementcited by 114
  9. 2019MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancementcited by 104
  10. 2020HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networkscited by 40
  11. 2020Self-Organized Operational Neural Networks with Generative Neuronscited by 38
  12. 2019Operational Neural Networkscited by 29
19 more
  1. 2020Self-Organized Operational Neural Networks for Severe Image Restoration Problemscited by 28
  2. 2017End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networkscited by 26
  3. 2020Improving GANs for Speech Enhancementcited by 22
  4. 2017Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognitioncited by 19
  5. 2020FastONN -- Python based open-source GPU implementation for Operational Neural Networkscited by 19
  6. 2018Heterogeneous Multilayer Generalized Operational Perceptroncited by 14
  7. 2020Exploiting Heterogeneity in Operational Neural Networks by Synaptic Plasticitycited by 14
  8. 2021Real-Time Patient-Specific ECG Classification by 1D Self-Operational Neural Networkscited by 13
  9. 2021Real-Time Glaucoma Detection from Digital Fundus Images using Self-ONNscited by 12
  10. 2021Robust Peak Detection for Holter ECGs by Self-Organized Operational Neural Networkscited by 11
  11. 2018Progressive Operational Perceptron with Memorycited by 9
  12. 2022Blind ECG Restoration by Operational Cycle-GANscited by 9
  13. 2022Global ECG Classification by Self-Operational Neural Networks with Feature Injectioncited by 9
  14. 2019Learning with Learned Loss Function: Speech Enhancement with Quality-Net to Improve Perceptual Evaluation of Speech Qualitycited by 8
  15. 2020Operational vs Convolutional Neural Networks for Image Denoisingcited by 8
  16. 2021BM3D vs 2-Layer ONNcited by 7
  17. 2021Super Neuronscited by 7
  18. 2020Speech Command Recognition in Computationally Constrained Environments with a Quadratic Self-organized Operational Layercited by 5
  19. 2022CycleGAN-Based Unpaired Speech Dereverberationcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 1.

3 papers.

  1. 2025SHIELD: A Secure and Highly Enhanced Integrated Learning for Robust Deepfake Detection against Adversarial Attackscited by 3
  2. 2023Exploring Sound vs Vibration for Robust Fault Detection on Rotating Machinerycited by 0
  3. 2024BRSR-OpGAN: Blind Radar Signal Restoration using Operational Generative Adversarial Networkcited by 0