ICASSP 2021 Deep Noise Suppression Challenge

TL;DR

The ICASSP 2021 Deep Noise Suppression Challenge aimed to advance noise suppression techniques through open datasets, evaluation frameworks, and community participation, highlighting ongoing challenges in real-time speech quality enhancement.

Contribution

This paper introduces expanded datasets, two challenge tracks, and a new non-intrusive speech quality metric to foster innovation in real-time noise suppression.

Findings

Community made significant progress in noise suppression.

Open datasets and metrics facilitated research and evaluation.

Challenges remain in achieving high speech quality in noisy conditions.

Abstract

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. 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 pick 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 are expanding both our training and test datasets. There are two tracks with one focusing on real-time denoising and the other focusing on real-time personalized deep noise suppression. We also make a non-intrusive objective speech quality metric called DNSMOS available for participants to use during their development stages. The final evaluation will be based on subjective tests.