mlsanityData to 7 Oct 2026

The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results

arXiv 2005.13981 ↗First posted 16 May 2020eess.AS cs.LG cs.SDcited by 128

Not on the map. Why?

Abstract (arXiv)

The INTERSPEECH 2020 Deep Noise Suppression (DNS) Challenge is intended to promote collaborative research in real-time single-channel Speech Enhancement aimed to maximize the subjective (perceptual) quality of the enhanced speech. A typical approach to evaluate the noise suppression methods is to use objective metrics on the test set obtained by splitting the original dataset. While the performance is good on the synthetic test set, often the model performance degrades significantly on real recordings. Also, most of the conventional objective metrics do not correlate well with subjective tests and lab subjective tests are not scalable for a large test set. In this challenge, we open-sourced a large clean speech and noise corpus for training the noise suppression models and a representative test set to real-world scenarios consisting of both synthetic and real recordings. We also open-sourced an online subjective test framework based on ITU-T P.808 for researchers to reliably test their developments. We evaluated the results using P.808 on a blind test set. The results and the key learnings from the challenge are discussed. The datasets and scripts can be found here for quick access https://github.com/microsoft/DNS-Challenge.

Key facts. Cited by 128 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 22; 2023: 24; 2024: 16; 2025: 27; 2026: 28.

128 papers.

Sort:

By area:

  1. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  2. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Modelscited by 195
  3. 2021NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasetscited by 189
  4. 2022Universal Speech Enhancement with Score-based Diffusioncited by 75
  5. 2023Generative Pre-training for Speech with Flow Matchingcited by 55
  6. 2021Interspeech 2021 Deep Noise Suppression Challengecited by 43
  7. 2024MaskSR: Masked Language Model for Full-band Speech Restorationcited by 24
  8. 2025AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancementcited by 23
  9. 2022RemixIT: Continual self-training of speech enhancement models via bootstrapped remixingcited by 20
  10. 2024Speech Robust Bench: A Robustness Benchmark For Speech Recognitioncited by 20
  11. 2021Transformers with Competitive Ensembles of Independent Mechanismscited by 19
  12. 2022SpeechLMScore: Evaluating speech generation using speech language modelcited by 19
38 more
  1. 2025LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancementcited by 19
  2. 2024NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcriptioncited by 18
  3. 2025FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matchingcited by 17
  4. 2025Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representationcited by 15
  5. 2022Speech Denoising in the Waveform Domain with Self-Attentioncited by 13
  6. 2022Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudescited by 10
  7. 2022Self-Supervised Learning for Speech Enhancement through Synthesiscited by 10
  8. 2022ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understandingcited by 8
  9. 2022LA-VocE: Low-SNR Audio-visual Speech Enhancement using Neural Vocoderscited by 8
  10. 2023Joint Prediction and Denoising for Large-scale Multilingual Self-supervised Learningcited by 8
  11. 2021InQSS: a speech intelligibility and quality assessment model using a multi-task learning networkcited by 7
  12. 2023Ultra Low Complexity Deep Learning Based Noise Suppressioncited by 7
  13. 2024Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speechcited by 7
  14. 2025Speech Enhancement Using Continuous Embeddings of Neural Audio Codeccited by 7
  15. 2025Multi-Metric Preference Alignment for Generative Speech Restorationcited by 7
  16. 2021Training Speech Enhancement Systems with Noisy Speech Datasetscited by 6
  17. 2021Continual self-training with bootstrapped remixing for speech enhancementcited by 6
  18. 2022Multi-View Attention Transfer for Efficient Speech Enhancementcited by 6
  19. 2023Rethinking complex-valued deep neural networks for monaural speech enhancementcited by 6
  20. 2023Dynamic nsNet2: Efficient Deep Noise Suppression with Early Exitingcited by 6
  21. 2021Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency Lossescited by 5
  22. 2022Phase-Aware Deep Speech Enhancement: It's All About The Frame Lengthcited by 5
  23. 2022Improving Speech Enhancement through Fine-Grained Speech Characteristicscited by 5
  24. 2022Speech separation with large-scale self-supervised learningcited by 5
  25. 2022SceneFake: An Initial Dataset and Benchmarks for Scene Fake Audio Detectioncited by 5
  26. 2024A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and Recognitioncited by 5
  27. 2024Dynamic Gated Recurrent Neural Network for Compute-efficient Speech Enhancementcited by 5
  28. 2024Joint Semantic Knowledge Distillation and Masked Acoustic Modeling for Full-band Speech Restoration with Improved Intelligibilitycited by 5
  29. 2025PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancementcited by 5
  30. 2026FlowSE-GRPO: Training Flow Matching Speech Enhancement via Online Reinforcement Learningcited by 5
  31. 2022Integrating Statistical Uncertainty into Neural Network-Based Speech Enhancementcited by 4
  32. 2023Unsupervised Data Selection for TTS: Using Arabic Broadcast News as a Case Studycited by 4
  33. 2023Interpretations of Domain Adaptations via Layer Variational Analysiscited by 4
  34. 2024RT-LA-VocE: Real-Time Low-SNR Audio-Visual Speech Enhancementcited by 4
  35. 2024SonicSim: A customizable simulation platform for speech processing in moving sound source scenarioscited by 4
  36. 2025Robust One-step Speech Enhancement via Consistency Distillationcited by 4
  37. 2025UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancementcited by 4
  38. 2021Toward Degradation-Robust Voice Conversioncited by 3

50 most cited of 128 All 128 (JSON)