# The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Speech Quality and Testing Framework

arXiv: https://arxiv.org/abs/2001.08662 · HTML: https://mlsanity.com/paper/2001.08662/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jan 2020.

## Built on by (most cited first, 11 of 11)

- [WavChat: A Survey of Spoken Dialogue Models](https://mlsanity.com/paper/2411.13577/) (2024)
- [CDPAM: Contrastive learning for perceptual audio similarity](https://mlsanity.com/paper/2102.05109/) (2021)
- [Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling](https://mlsanity.com/paper/2209.15483/) (2022)
- [End-to-End Complex-Valued Multidilated Convolutional Neural Network for Joint Acoustic Echo Cancellation and Noise Suppression](https://mlsanity.com/paper/2110.00745/) (2021)
- [Perceptual-based deep-learning denoiser as a defense against adversarial attacks on ASR systems](https://mlsanity.com/paper/2107.05222/) (2021)
- [Knowing When to Quit: Probabilistic Early Exits for Speech Separation](https://mlsanity.com/paper/2507.09768/) (2025)
- [CORN: Co-Trained Full- And No-Reference Speech Quality Assessment](https://mlsanity.com/paper/2310.09388/) (2023)
- [DroneAudioset: An Audio Dataset for Drone-based Search and Rescue](https://mlsanity.com/paper/2510.15383/) (2025)
- [Task-aware Warping Factors in Mask-based Speech Enhancement](https://mlsanity.com/paper/2108.12128/) (2021)
- [Speech Enhancement with Perceptually-motivated Optimization and Dual Transformations](https://mlsanity.com/paper/2209.11905/) (2022)
- [Audio-FLAN: An Instruction-Following Dataset for Unified Audio Understanding and Generation of Speech, Music, and Sound](https://mlsanity.com/paper/2502.16584/) (2025)

## Abstract (arXiv)

The INTERSPEECH 2020 Deep Noise Suppression 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. Many publications report reasonable performance on the synthetic test set drawn from the same distribution as that of the training set. However, 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-source 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 source an online subjective test framework based on ITU-T P.808 for researchers to quickly test their developments. The winners of this challenge will be selected based on subjective evaluation on a representative test set using P.808 framework.