Skip to content

Acoustic Scene Classification System (DCASE2018 Task 1)

License

Notifications You must be signed in to change notification settings

dangpzanco/dcase-task1

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Classificação de Cenas Acústicas Utilizando Técnicas de Aprendizagem Profunda

Paper

https://biblioteca.sbrt.org.br/articles/1929

Bachelor Thesis

https://repositorio.ufsc.br/handle/123456789/193287

Abstract

This paper presents new contributions aiming at enhancing the performance of the baseline acoustic scene classifier proposed in the context of the Detection and Classification of Acoustic Scenes and Events 2018 (DCASE2018) Challenge. These contributions consist on modifications of the structure of the baseline convolutional neural network as well as on the use of data augmentation and model ensemble strategies. As a result, an accuracy of 72.04% is obtained for the development dataset, whereas 68.5% accuracy is obtained for the evaluation dataset. This corresponds to a significantly better performance in comparison with the baseline system, which is of 59.7% and 61.0%, respectively.

Releases

No releases published

Packages

No packages published

Languages