Sound Event Detection in Synthetic Audio: Analysis of the DCASE 2016 Task Results

TL;DR

This paper analyzes the performance of sound event detection systems on synthetic office audio mixtures from the DCASE 2016 challenge, highlighting how algorithms handle noise and polyphony with precise ground truth.

Contribution

It provides a comprehensive analysis of system performance on synthetic data, including evaluation metrics, submitted systems, and statistical insights into algorithm behavior under controlled conditions.

Findings

Algorithms' robustness varies with noise levels

Polyphony impacts detection accuracy significantly

Evaluation metrics reveal strengths and weaknesses of submitted systems

Abstract

As part of the 2016 public evaluation challenge on Detection and Classification of Acoustic Scenes and Events (DCASE 2016), the second task focused on evaluating sound event detection systems using synthetic mixtures of office sounds. This task, which follows the `Event Detection - Office Synthetic' task of DCASE 2013, studies the behaviour of tested algorithms when facing controlled levels of audio complexity with respect to background noise and polyphony/density, with the added benefit of a very accurate ground truth. This paper presents the task formulation, evaluation metrics, submitted systems, and provides a statistical analysis of the results achieved, with respect to various aspects of the evaluation dataset.