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

Sound event detection in synthetic domestic environments

Abstract : We present a comparative analysis of the performance of state-of-the-art sound event detection systems. In particular, we study the robustness of the systems to noise and signal degradation, which is known to impact model generalization. Our analysis is based on the results of task 4 of the DCASE 2019 challenge, where submitted systems were evaluated on, in addition to real-world recordings, a series of synthetic soundscapes that allow us to carefully control for different soundscape characteristics. Our results show that while overall systems exhibit significant improvements compared to previous work, they still suffer from biases that could prevent them from generalizing to real-world scenarios.
Complete list of metadata

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/hal-02355573
Contributor : Romain Serizel Connect in order to contact the contributor
Submitted on : Friday, November 8, 2019 - 12:26:53 PM
Last modification on : Saturday, October 16, 2021 - 11:26:10 AM
Long-term archiving on: : Sunday, February 9, 2020 - 7:06:29 PM

File

Template.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02355573, version 1

Citation

Romain Serizel, Nicolas Turpault, Ankit Shah, Justin Salamon. Sound event detection in synthetic domestic environments. 2019. ⟨hal-02355573v1⟩

Share

Metrics

Record views

168

Files downloads

255