Speaker: Almudena Aguilera
Abstract: The experiment is based on the dataset from Voxceleb [1], using the two pre-trained models. The main idea of these experiments was to study the fairness problems in different demographic groups present in the data base of Voxceleb1. The use of the data base Voxceleb1 instead of Voxceleb2, it is fundamentally because sensitive attributes such as gender and nationality are not presented in this database information, making it impossible to generate split lists on those attributes. The “Voxceleb Experiment†showed, make one experiment to see that the dataset works correctly, and three more comparing: gender, nationality, and both attributes together.