{"id":701872,"date":"2020-11-13T12:25:52","date_gmt":"2020-11-13T20:25:52","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-academic-program&p=701872"},"modified":"2023-10-04T13:36:26","modified_gmt":"2023-10-04T20:36:26","slug":"deep-noise-suppression-challenge-interspeech-2020","status":"publish","type":"msr-academic-program","link":"https:\/\/www.microsoft.com\/en-us\/research\/academic-program\/deep-noise-suppression-challenge-interspeech-2020\/","title":{"rendered":"Deep Noise Suppression Challenge – INTERSPEECH 2020"},"content":{"rendered":"\n\n

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

The application period is now closed.<\/strong><\/p>\n

Program dates:<\/strong> March-July 2020<\/p>\n

Contact us:<\/strong> If you have questions about this program, email us at dns_challenge@microsoft.com<\/a>.<\/p>\n

Other challenges:<\/strong><\/p>\n

Deep Noise Suppression Challenge – ICASSP 2021<\/a><\/p>\n

Acoustic Echo Cancellation Challenge – ICASSP 2021<\/a><\/p>\n

Acoustic Echo Cancellation Challenge – INTERSPEECH 2021<\/a><\/p>\n

Acoustic Echo Cancellation Challenge – ICASSP 2022<\/a><\/p>\n

Deep Noise Suppression Challenge – ICASSP 2022<\/a><\/p>\n

The DNS Challenge at INTERSPEECH 2020<\/a> is intended to promote collaborative research in single-channel Speech Enhancement aimed to maximize the perceptual quality and intelligibility of the enhanced speech. The challenge will evaluate the speech quality using the online subjective evaluation framework ITU-T P.808<\/a>. The challenge provides large datasets<\/a> for training noise suppressors, but allows participants to use any datasets of their choice. Participants can also augment their datasets with the provided data. The challenge also provides a test set that is very extensive. The test set contains both synthetic noisy speech and also real recordings. The final evaluation will be conducted on a blind test set that is similar to the open sourced test set. We also provide model and inference scripts for a baseline noise suppressor that was recently published<\/a>.<\/p>\n

More details about the open sourced data, baseline noise suppressor, ITU-T P.808 and DNS challenge can be found here<\/a>.<\/p>\n

Submitted papers will fall under one of these two tracks based on the computational complexity.<\/p>\n