The goals of this project are the creation of a new dataset of sounds that belong to the domestic... more 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-trust...
Zenodo (CERN European Organization for Nuclear Research), Oct 31, 2018
My supervisor Eduardo Fonseca, whose expertise, diligence, patience and constant encouragement we... more My supervisor Eduardo Fonseca, whose expertise, diligence, patience and constant encouragement were crucial for going through with this thesis • My co-supervisor Frederic Font, for the valuable input • All the people of the MTG behind the Freesound Datasets platform that helped me with the understanding and the exploitation of the platform and the resources • My family, for the constant love and support
Uploads
Papers by Aniel Rossi