Sound Event Detection in Synthetic Domestic Environments
By Romain Serizel, Nicolas Turpault, Ankit Shah, Justin Salamon. 2020
112 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Eduardo Fonseca
- Romain Serizel
- Nicolas Turpault
- D. Ellis
- John R. Hershey
- Prem Seetharaman
- Justin Salamon
- Scott Wisdom
In Signal Processing
- Eduardo Fonseca
- John R. Hershey
- Scott Wisdom
- Hakan Erdogan
- Prem Seetharaman
- D. Ellis
- Romain Serizel
- Nicolas Turpault
Citations in the corpus
- FSD50K: An Open Dataset of Human-Labeled Sound Events (2020, neutral): “This could allow defining robustness tasks such as training or evaluating with a subset of data of more adverse conditions, similarly as done in [58] for SED or with ImageNet-A for image recognition [59].”
- Improving Sound Event Detection in Domestic Environments using Sound Separation (2020, methodology): “The dataset used for the SED experiments is DESED(1), a flexible dataset for SED in domestic environments composed of 10-sec audio clips that are recorded or synthesized [13, 4].”
- HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection (2022, unknown): “In this section, we evaluate the performance of HTS-AT in four datasets: the event classification on AudioSet [7], ESC-50 [8]; the keyword spotting on Speech Command V2 [4]; and additionally, the event detection on DESED [18].”
- What’s all the Fuss about Free Universal Sound Separation Data? (2020, methodology): “Sound separation can be used for SED by first separating the component sounds in a mixed signal and then applying SED on each of the separated tracks [15, 7, 16, 17, 18].”