Thesis Open Access

Event Recognition of Domestic Sounds using Semi-Supervised Learning

Rossi, Aniel

Thesis supervisor(s)

Fonseca, Eduardo; Font, Frederic

The goals of this project are the creation of a new dataset of sounds that belong to the domestic environment, called DomesticFSD2018, and to research on methods for the automatic classification of them. A Semi-Supervised approach is used to evaluate the possibility of exploiting samples that are not manually-verified. The purpose of this is to avoid the need of experts and save as many resources as possible in the validation process, that usually takes a lot of time and energies. The train set of DomesticFSD2018 is composed of a trustable (manually-verified) portion of data and a non-trustable (which has received no human validation and can be potentially inaccurate or mislabeled) one. A purely supervised learning approach is firstly followed, training models with only the trustable portion, and both trustable and non-trustable portions of data. Then the semi-supervised learning approach is experimented, using the models trained in the previous step to make predictions on non-trustable data. The samples predicted with the highest level of confidence are added to the train set, and finally, the classifier is re-trained using the updated and larger train set. In both cases, the technologies used are Support Vector Machines using MFCCs’ properties as input. The semi-supervised approach shows better results and allows us to add a considerable amount of non-trustable data to the trustable portion of the dataset.

Files (1.8 MB)
Name Size
1.8 MB Download
All versions This version
Views 122122
Downloads 8686
Data volume 155.1 MB155.1 MB
Unique views 107107
Unique downloads 8282


Cite as