Khan, Umair (Date of defense: 2021-01-11)
In speaker recognition, i-vectors have been the state-of-the-art unsupervised technique over the last few years, whereas x-vectors is becoming the state-of-the-art supervised technique, these days. ...
Varas González, David (Date of defense: 2016-11-14)
In this thesis, we exploit the hierarchical information associated with images to tackle two fundamental problems of computer vision: video object segmentation and video segmentation. In the first part ...
Girbau Xalabarder, Andreu (Date of defense: 2021-03-17)
Since less than a decade ago, deep learning techniques started to dominate many different fields, revolutionizing the possibilities of artificial intelligence. Seeing their potential, industrial sectors ...
Escolano Peinado, Carlos (Date of defense: 2022-03-18)
This thesis aims to study different language-specific approaches for Multilingual Machine Translation without parameter sharing and their properties compared to the current state-of-the-art based on ...
Castro-Arvizu, Juan Manuel (Date of defense: 2017-03-24)
Navigation and location technologies have been reaching in a major interest where Global Navigation Satellite System (GNSS) is mostly adopted. The limitation of this technology is that direct sky view ...
Zhao, Feng, 1992- (Date of defense: 2019-07-26)
Ground deformation measurements can provide valuable information for minimization of associated loss and damage caused by natural and environmental hazards. As a kind of remote sensing technique, ...
Locatelli, Fabiano (Date of defense: 2021-11-18)
One of the possible ways to address the constantly increasing amount of heterogeneous and variable internet traffic is the evolution of the current optical networks towards a more flexible, open, and ...
Pascual De La Puente, Santiago (Date of defense: 2020-01-31)
Deep learning has affected the speech processing and generation fields in many directions. First, end-to-end architectures allow the direct injection and synthesis of waveform samples. Secondly, the ...
Salvador, Amaia (Date of defense: 2019-06-27)
In the past decade, deep neural networks have revolutionized computer vision. High performing deep neural architectures trained for visual recognition tasks have pushed the field towards methods relying ...
Pujol Miró, Alba (Date of defense: 2020-09-18)
The ability to capture depth information form an scene has greatly increased in the recent years. 3D sensors, traditionally high cost and low resolution sensors, are being democratized and 3D scans of ...