27 October 2022
A central question in automatic speech processing is how and what representations to use, to facilitate further processing and to apply machine learning methods to automate speech processing tasks. A focus in this thesis is on training neural network models and learning representations from the speech data itself. To that end, unsupervised and self-supervised speech models are proposed. Furthermore, several contributions to German speech recognition and automatic subtitle generation are presented.
Date and Time: Thursday, 27.10.2022, 16:00 CET
Location: University of Hamburg, Informatikum Campus, Room D125/129