ICASSP 2021 Deep Noise Suppression Challenge

By Chandan K. A. Reddy, Harishchandra Dubey, Vishak Gopal, Ross Cutler, Sebastian Braun, Hannes Gamper, Robert Aichner, Sriram Srinivasan. 2020

161 citations recorded by the source corpus.

The Deep Noise Suppression (DNS) challenge is designed to foster innovation in the area of noise suppression to achieve superior perceptual speech quality. We recently organized a DNS challenge special session at INTERSPEECH 2020 where we open-sourced training and test datasets for researchers to train their noise suppression models. We also open-sourced a subjective evaluation framework and used the tool to evaluate and select the final winners. Many researchers from academia and industry made significant contributions to push the field forward. We also learned that as a research community, we still have a long way to go in achieving excellent speech quality in challenging noisy real-time conditions. In this challenge, we expanded both our training and test datasets. Clean speech in the training set has increased by 200% with the addition of singing voice, emotion data, and non-English languages. The test set has increased by 100% with the addition of singing, emotional, non-English (tonal and non-tonal) languages, and, personalized DNS test clips. There are two tracks with focus on (i) real-time denoising, and (ii) real-time personalized DNS. We present the challenge results at the end.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing (2021, background): “NSNet2 is the baseline model on the 2020 Deep Noise Suppression (DNS) challenge (Reddy et al., 2021) and obtains WER of 45.8%, probably due to the mismatch between the noise intensity of the WHAM! and DNS corpus.”
Icassp 2022 Deep Noise Suppression Challenge (2022, background): “In recent years, deep learning based approaches have shown promising results for superior speech quality [2, 3, 4].”
End-to-End Neural Speech Coding for Real-Time Communications (2022, positive): “We synthesized 890 hours of 16khz noisy audios with clean speech, noises and room impulses from the Deep Noise Suppression Challenge at ICASSP 2021 [18].”
Dnsmos: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors (2020, methodology): “In order to test the generalization capability of training multiple stages of selfteaching models, we evaluated on the ICASSP 2021 DNS Challenge 2 final submissions [20], which comprised of the blind test set processed by 18 different noise suppressors.”
Cross-Scale Vector Quantization for Scalable Neural Speech Coding (2022, methodology): “We take 150 hours of 16kHz multilingual clean speech from the DNS Challenge at ICASSP 2021 dataset [26].”
Interspeech 2021 Deep Noise Suppression Challenge (2021, background): “The Deep Noise Suppression (DNS) Challenge organized at INTERSPEECH 2020 [6] and ICASSP 2020 [7] showed great progress, while also indicating that we are still about 1.”
Subjective Evaluation of Noise Suppression Algorithms in Crowdsourcing (2021, methodology): “Our P.835 tool was used in the the INTERSPEECH 2021 Deep Noise Suppression Challenge [1] as the primary evaluation metric.”