Sound Event Detection and Separation: a Benchmark on Desed Synthetic Soundscapes
Sound
2020-11-03 v1 Audio and Speech Processing
Abstract
We propose a benchmark of state-of-the-art sound event detection systems (SED). We designed synthetic evaluation sets to focus on specific sound event detection challenges. We analyze the performance of the submissions to DCASE 2021 task 4 depending on time related modifications (time position of an event and length of clips) and we study the impact of non-target sound events and reverberation. We show that the localization in time of sound events is still a problem for SED systems. We also show that reverberation and non-target sound events are severely degrading the performance of the SED systems. In the latter case, sound separation seems like a promising solution.
Keywords
Cite
@article{arxiv.2011.00801,
title = {Sound Event Detection and Separation: a Benchmark on Desed Synthetic Soundscapes},
author = {Nicolas Turpault and Romain Serizel and Scott Wisdom and Hakan Erdogan and John Hershey and Eduardo Fonseca and Prem Seetharaman and Justin Salamon},
journal= {arXiv preprint arXiv:2011.00801},
year = {2020}
}