Now showing items 21-40 of 47

    Large vocabulary continuous speech recognition for the transcription of Catalan broadcast news and conversations : towards analysis and modelling of acoustic reduction in spontaneous speech 

    Schulz, Henrik (Date of defense: 2017-03-02)

    The transcription of spontaneous speech still poses a challenge to state-of-the-art methods for automatic speech recognition. The present thesis describes the comprehensive development of a large vocabulary continuous ...

    Learning multilingual and multimodal representations with language-specific encoders and decoders for machine translation 

    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 parameter-sharing. We ...

    Learning to extract features for 2D – 3D multimodal registration 

    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 indoor and outdoor ...

    Machine learning assisted QoT estimation for optical networks optimization 

    Mahajan, Ankush (Date of defense: 2021-09-28)

    The tremendous increase in data traffic has spurred a rapid evolution of the optical networks for a reliable, affordable, cost effective and scalable network infrastructure. To meet some of these requirements, network ...

    Machine learning techniques for adaptive polynomial and neural network digital predistorters 

    López Bueno, David (Date of defense: 2023-07-07)

    (English) The power amplifier (PA) is a core element in the radio transmitters to support the required mobile and fixed broadband communication link ranges. However, the PA is a power-hungry and nonlinear by nature device. ...

    Matrix completion with prior information in reproducing kernel Hilbert spaces 

    Giménez Febrer, Pere Joan (Date of defense: 2021-02-11)

    In matrix completion, the objective is to recover an unknown matrix from a small subset of observed entries. Most successful methods for recovering the unknown entries are based on the assumption that the unknown full ...

    Monocular depth estimation in images and sequences using occlusion cues 

    Palou Visa, Guillem (Date of defense: 2014-02-21)

    When humans observe a scene, they are able to perfectly distinguish the different parts composing it. Moreover, humans can easily reconstruct the spatial position of these parts and conceive a consistent structure. The ...

    Network virtualization in next generation cellular networks 

    Tseliou, Georgia (Date of defense: 2019-07-17)

    The complexity of operation and management of emerging cellular networks significantly increases, as they evolve to correspond to increasing QoS needs, data rates and diversity of offered services. Thus critical challenges ...

    On the detection of ionospheric waves, relationship with earthquakes and tsunamis 

    Yang, Heng, 1985- (Date of defense: 2019-06-11)

    The research of this thesis addresses the detection and characterization of ionospheric waves and its application to traveling ionospheric disturbances (TIDs) induced by the natural events, such as earthquakes and tsunamis. ...

    Parallel scalability of face detection in heterogeneous multithreaded architectures 

    Oro García, David (Date of defense: 2020-11-17)

    Recently, facial recognition systems have become extremely popular and deployments of this technology are now ubiquitous. Applications ranging from access control to automated surveillance of video feeds rely on facial ...

    Parametric region-based foreround segmentation in planar and multi-view sequences 

    Gallego Vila, Jaime (Date of defense: 2013-10-14)

    Foreground segmentation in video sequences is an important area of the image processing that attracts great interest among the scientist community, since it makes possible the detection of the objects that appear in the ...

    Part-based object retrieval with binary partition trees 

    Giró i Nieto, Xavier (Date of defense: 2012-05-31)

    This thesis addresses the problem of visual object retrieval, where a user formulates a query to an image database by providing one or multiple examples of an object of interest. The presented techniques aim both at finding ...

    Radio and computing resource management in SDR clouds 

    Gómez, Ismael (Date of defense: 2013-12-19)

    The aim of this thesis is defining and developing the concept of an efficient management of radio and computing resources in an SDR cloud. The SDR cloud breaks with today's cellular architecture. A set of distributed ...

    Region-based particle filter leveraged with a hierarchical co-clustering 

    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 of the thesis, we ...

    Robust indoor positioning in WLAN networks 

    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 is needed for reliable ...

    Robust speaker diarization for meetings 

    Anguera Miró, Xavier (Date of defense: 2006-12-21)

    Aquesta tesi doctoral mostra la recerca feta en l'àrea de la diarització de locutor per a sales de reunions. En la present s'estudien els algorismes i la implementació d'un sistema en diferit de segmentació i aglomerat de ...

    Self-managed resources in network virtualisation environments 

    Mijumbi, Rashid (Date of defense: 2014-11-06)

    Network virtualisation is a promising technique for dealing with the resistance of the Internet to architectural changes, enabling a novel business model in which infrastructure management is decoupled from service ...

    Self-supervised deep learning approaches to speaker recognition 

    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. Recent advances in Deep ...

    Sistemas de teledetección activos y pasivos embarcados en sistemas aéreos no tripulados para la monitorización de la tierra 

    Acevo Herrera, René (Date of defense: 2011-04-04)

    La comunidad científica ha mostrado gran interés por estudiar los fenómenos que ocurren sobre la superficie de la tierra, específicamente los que suceden en la atmósfera, los océanos, o la superficie del suelo, y que afectan ...

    Speaker diarization and tracking in multiple-sensor environments 

    Luque Serrano, Jordi (Date of defense: 2012-12-21)

    This thesis verses about the research conducted in the topic of speaker recognition in real conditions like as meeting rooms, telephone quality speech and radio and TV broadcast news. The main objective is concerned to the ...