Top Ranks for CP Teams and JKU Students in the DCASE 2022 Challenge
CP Teams and JKU Students participate successfully in the tasks "Low-Complexity Acoustic Scene Classification/ and /Automated Audio
The CP Team (Florian Schmid, Shahed Masoudian, Khaled Koutini & Gerhard Widmer) and a JKU Student Team (Tobias Morocutti and Diaaeldin Shalaby,
supervised by CP members) score ranks 1 and 3 in the Low-Complexity Acoustic Scene Classification Task, öffnet eine externe URL in einem neuen Fenster of the DCASE 2022 Challenge. The aim of this task is to classify audio
recordings into one of ten predefined acoustic scenes. Submitted Systems have to overcome hurdles such as low-complexity constraints, cross-device and cross-city generalization.
The CP Team (Paul Primus & Gerhard Widmer) achieves rank 4 in the Automated Audio Captioning Task, öffnet eine externe URL in einem neuen Fenster of the DCASE 2022 Challenge. The goal of this task is to build a system that accepts an audio signal as input and outputs a textual description.