Sound Event Detection in Synthetic Audio: Analysis of the DCASE 2016 Task Results
This work provides insights for researchers in audio processing by benchmarking sound event detection methods on synthetic data, but it is incremental as it builds on prior DCASE tasks.
The paper analyzed results from the DCASE 2016 task on sound event detection in synthetic audio, focusing on how algorithms performed under controlled noise and polyphony conditions, with detailed statistical evaluation of submitted systems.
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.