This competition is framed under the fourth edition of the [Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge](http://dcase.community/challenge2018/). Building up on the success of the previous editions, DCASE 2018 Challenge continues supporting the development of computational scene and event analysis methods by comparing different approaches using common publicly available datasets. 

DCASE 2018 Challenge features 5 tasks, this one is [Task 2](http://dcase.community/challenge2018/task-general-purpose-audio-tagging). The timeline is shared among all tasks and participants are welcome to compete in other tasks as well.

While a technical report is not required for the Kaggle competition, participants of the other DCASE Tasks are expected to submit a technical report because the challenge is premised upon the sharing of ideas and results. The technical report will describe the submitted system and will help the community better understand how the algorithm works. Therefore, **we encourage participants to submit a technical report through DCASE submission system**. The technical reports will be eventually published on the DCASE Challenge website. More info will be available in the [DCASE submission page](http://dcase.community/challenge2018/submission).

Results of the DCASE Challenge are typically presented in the [DCASE Workshop](http://dcase.community/workshop2018/index), which takes place a couple of months after the Challenge finishes. The workshop aims to provide a venue for researchers working on computational analysis of sound events and scene analysis to present and discuss their results. **We also encourage participants to submit a full scientific paper to the DCASE 2018 Workshop**, which will be held in November 2018, Surrey, UK. In this case, the paper must respect the structure of a scientific publication and the papers will be peer-reviewed. More info will be available in the Workshop paper instructions site.

Should you have any doubts, please contact frederic.font@upf.edu or eduardo.fonseca@upf.edu.

Relevant links:

 - Quick glance on both DCASE 2018 Workshop and Challenge: http://dcase.community/
 - Last year’s DCASE Workshop: http://www.cs.tut.fi/sgn/arg/dcase2017/workshop/ 


----------

### Citing this competition
<a name="#DCASE_citing">

We have submitted a paper to the DCASE Workshop describing this competition. The goal of this publication is that participants can cite it when referring to details of the task, dataset, baseline, etc. The paper is now available on Arxiv. If you are participating to this competition or using the dataset or baseline code please cite the following paper:

> Eduardo Fonseca, Manoj Plakal, Frederic Font, Daniel P. W. Ellis,
> Xavier Favory, Jordi Pons, Xavier Serra. *General-purpose Tagging of
> Freesound Audio with AudioSet Labels: Task Description, Dataset, and
> Baseline*. Submitted to DCASE2018 Workshop, 2018. URL:
> https://arxiv.org/abs/1807.09902