VOICe: A Sound Event Detection Dataset For Generalizable Domain Adaptation
By Shayan Gharib, Konstantinos Drossos, Eemi Fagerlund, Tuomas Virtanen. 2019
4 citations recorded by the source corpus.
The performance of sound event detection methods can significantly degrade when they are used in unseen conditions (e.g. recording devices, ambient noise). Domain adaptation is a promising way to tackle this problem. In this paper, we present VOICe, the first dataset for the development and evaluation of domain adaptation methods for sound event detection. VOICe consists of mixtures with three different sound events ("baby crying", "glass breaking", and "gunshot"), which are over-imposed over three different categories of acoustic scenes: vehicle, outdoors, and indoors. Moreover, the mixtures are also offered without any background noise. VOICe is freely available online (this https URL). In addition, using an adversarial-based training method, we evaluate the performance of a domain adaptation method on VOICe.
Subfields: Artificial Intelligence, 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 Artificial Intelligence
- Xavier Serra
- Eduardo Fonseca
- Jordi Pons
- Xavier Favory
- Frederic Font
- Yossi Adi
- Lauri Juvela
- Paavo Alku
In Signal Processing
- Eduardo Fonseca
- Xavier Serra
- Frederic Font
- Xavier Favory
- Jordi Pons
- Andrés Ferraro
- Jakob Abeßer
- D. Ellis
Citations in the corpus
- FSD50K: An Open Dataset of Human-Labeled Sound Events (2020, methodology): “Other instances of this approach include TAU Spatial Sound Events 2019 [29], for sound event detection and localization, and VOICe [30] for the study of domain adaptation in SED.”