Sound Event Detection in Domestic Environments


Task description

Coordinators

Romain Serizel
Francesca Ronchini
Francesca Ronchini
Janek Ebbers
Florian Angulo
Florian Angulo
David Perera
David Perera
Slim Essid
Slim Essid
Annamaria Mesaros
Annamaria Mesaros
Irene Martin Morato
Irene Martin Morato
Toni Heittola
Toni Heittola

The goal of this task is to evaluate systems for the detection of sound events using real data, with different types of annotations data and corresponding labels available for training.

Challenge has ended. Full results for this task can be found in subtask specific result pages: Task4A Task4B

If you are interested in the task, you can join us on the dedicated slack channel

Description

The target of the systems is to provide the event class and the event time localization given that multiple events can be present in an audio recording (see Fig. 1). The types of data available for training are weakly-labeled or unlabeled short real audio recordings, strongly-labeled synthetic audio, and softly-labeled long real recordings.

Figure 1: Overview of a sound event detection system.


We provide two subtasks:

A Weak Task 4

Sound Event Detection with Weak Labels and Synthetic Soundscapes
Subtask A

The goal of the task is to evaluate systems for the detection of sound events using real data either weakly labeled or unlabeled and simulated data that is strongly labeled (with time stamps).

Subtask A


B Soft Task 4

Sound Event Detection with Soft Labels
Subtask B

The goal of this task is to evaluate systems for the detection of sound events that use softly labeled data for training in addition to other types of data such as weakly labeled, unlabeled or strongly labeled. The main focus of this subtask is to investigate whether using soft labels brings any improvement in performance.

Subtask B