Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Sound Event Detection and Separation: a Benchmark on Desed Synthetic Soundscapes

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.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

Cited literature [33 references]  Display  Hide  Download
Contributor : Romain Serizel Connect in order to contact the contributor
Submitted on : Saturday, October 31, 2020 - 6:37:54 PM
Last modification on : Wednesday, November 3, 2021 - 7:56:49 AM
Long-term archiving on: : Monday, February 1, 2021 - 6:16:18 PM


Files produced by the author(s)


  • HAL Id : hal-02984675, version 1
  • ARXIV : 2011.00801



Nicolas Turpault, Romain Serizel, Scott Wisdom, Hakan Erdogan, John Hershey, et al.. Sound Event Detection and Separation: a Benchmark on Desed Synthetic Soundscapes. 2020. ⟨hal-02984675⟩



Record views


Files downloads