{"id":702019,"date":"2020-11-13T12:30:24","date_gmt":"2020-11-13T20:30:24","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-academic-program&p=702019"},"modified":"2023-10-04T13:36:50","modified_gmt":"2023-10-04T20:36:50","slug":"deep-noise-suppression-challenge-icassp-2021","status":"publish","type":"msr-academic-program","link":"https:\/\/www.microsoft.com\/en-us\/research\/academic-program\/deep-noise-suppression-challenge-icassp-2021\/","title":{"rendered":"Deep Noise Suppression Challenge – ICASSP 2021"},"content":{"rendered":"\n\n

<\/p>\n\n\n\n\n\n\n

Program dates:<\/strong> September 2020-January 2021<\/p>\n

The ICASSP 2021 Deep Noise Suppression (DNS) challenge is designed to foster innovation in the field of noise suppression to achieve superior perceptual speech quality. We recently organized a DNS challenge special session at INTERSPEECH 2020<\/a>. We open sourced training and test datasets<\/a> for researchers to train their noise suppression models. We also open sourced a subjective evaluation framework<\/a> 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. The results<\/a> of the INTERSPEECH DNS Challenge show we still have a long way to go in achieving superior speech quality in challenging noisy conditions. In this challenge, we will be adding over 20 hours of clean speech with singing and provide more information about the characteristics of the noise based on stationarity. We will also provide over 100000 synthetic and real room impulse responses (RIRs) curated from other data sets.<\/p>\n

We will have two tracks for this challenge:<\/p>\n