DCASE 2017 Challenge setup: Tasks, datasets and baseline system

Annamaria Mesaros (1) , Toni Heittola (1) , Aleksandr Diment (1) , Benjamin Elizalde (2) , Ankit Shah (2) , Emmanuel Vincent (3) , Bhiksha Raj (2) , Tuomas Virtanen (1)

1 TUT - Tampere University of Technology [Tampere]
2 Computer Science Department - Carnegie Mellon University
3 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication

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.

Mots clés: Sound scene analysis; Acoustic scene classification; Sound event detection; Audio tagging; Rare sound events; Weak labels

Domaines: Traitement du signal et de l'image [eess.SP]

Annamaria Mesaros, Toni Heittola, Aleksandr Diment, Benjamin Elizalde, Ankit Shah, et al.. DCASE 2017 Challenge setup: Tasks, datasets and baseline system. DCASE 2017 - Workshop on Detection and Classification of Acoustic Scenes and Events, Nov 2017, Munich, Germany. ⟨hal-01627981⟩