DCASE 2017 challenge setup: tasks, datasets and baseline system

Mesaros, Annamaria; Heittola, Toni; Diment, Aleksandr; Elizalde, {Benjamin Martinez}; Shah, Ankit; Vincent, Emmanuel; Raj, Bhiksha; Virtanen, Tuomas

DCASE 2017 Challenge consists of four tasks: acoustic scene classification, detection of rare sound events, sound event detection in real-life audio, and large-scale weakly supervised sound event detection for smart cars. This paper presents the setup of these tasks: task definition, dataset, experimental setup, and baseline system results on the development dataset. The baseline systems for all tasks rely on the same implementation using multilayer perceptron and log mel-energies, but differ in the structure of the output layer and the decision making process, as well as the evaluation of system output using task specific metrics.


Sound scene analysis; Acoustic scene classification; Sound event detection; Audio tagging; Rare sound events

Book title:
Proceedings of the Detection and Classification of Acoustic Scenes and Events 2017 Workshop (DCASE2017)