*L3DAS22: Machine Learning for 3D Audio Signal Processing* Signal Processing Grand Challenge at IEEE ICASSP 2022
Scope of the Challenge The *L3DAS22 Challenge* aims at encouraging and fostering research on machine learning for 3D audio signal processing. The challenge presents two tasks, both relying on first-order Ambisonics (FOA) recordings in a real reverberant office environment. Each task involves 1-mic and 2-mic FOA recordings. § Task 1 – 3D Speech Enhancement Models are expected to extract the monophonic voice signal from the 3D mixture containing various background noises. The evaluation metric is a combination of STOI and WER measures. § Task 2 –3D Sound Event Localization and Detection Models must predict a list of the active sound events and their respective location at regular intervals of 100 milliseconds. Performance is evaluated according to localization and detection error metrics. Additional Info § Prizes will be awarded to the *challenge winners* thanks to the support of Kuaishou Technology. § *Top 5 ranked teams* can submit a regular paper according to the ICASSP guidelines. § All participants will have the possibility to upload an *interactive demo* of their models on Replicate <https://replicate.ai/>. § Please visit the Challenge website <https://www.l3das.com/icassp2022/index.html> for further information, including: challenge rules <https://www.l3das.com/icassp2022/rules.html>, registration <https://www.l3das.com/icassp2022/registration.html>, datasets download <https://www.kaggle.com/l3dasteam/l3das22>, results submission <https://www.l3das.com/icassp2022/submission.html>, documentation <https://www.l3das.com/assets/file/L3DAS22_ICASSP_documentation.pdf>, and official GitHub repository <https://github.com/l3das/L3DAS22>. Timeline § Nov 22, 2021 – Release of Datasets, Code, Baseline Methods and Documentation § Dec 22, 2021 – Deadline for Submitting Results for Both Tasks § Jan 20, 2022 – Deadline for Paper Submission (Top Ranked 5 Only) § Feb 10, 2022 – Grand Challenge Paper Acceptance Notification Organizers Danilo Comminiello, Sapienza University of Rome, Italy Eric Guizzo, Sapienza University of Rome, Italy Xinlei Ren, Kuaishou Technology, Beijing, China Christian Marinoni, Sapienza University of Rome, Italy Marco Pennese, Sapienza University of Rome, Italy Xiguang Zheng, Kuaishou Technology, Beijing, China Chen Zhang, Kuaishou Technology, Beijing, China Bruno Masiero, University of Campinas, Brazil Challenge Website and Contacts § L3DAS22 Challenge Website: www.l3das.com/icassp2022 <https://www.l3das.com/icassp2022/index.html> § Email contact: [email protected] § Twitter: https://twitter.com/das_l3 -------------- next part -------------- An HTML attachment was scrubbed... URL: <https://mail.music.vt.edu/mailman/private/sursound/attachments/20211123/4ed19d15/attachment.htm> _______________________________________________ Sursound mailing list [email protected] https://mail.music.vt.edu/mailman/listinfo/sursound - unsubscribe here, edit account or options, view archives and so on.
