2025

In everyday communication scenarios, such as meetings and social gatherings, undesired interfering speakers and background noise often degrade the quality and intelligibility of the desired target speaker. Various approaches have been developed to address this issue, such as blind source separation and speaker-conditioned target speaker extraction (SC-TSE). SC-TSE algorithms aim at extracting the desired speaker…

In many speech communication devices, such as smartphones, smartspeakers, and hearing devices, the microphones capture not only the target speaker but also undesired ambient noise, degrading speech quality and speech intelligibility. Speech enhancement algorithms aim at extracting the target speech from the recorded microphone signals by suppressing noise while not distorting the target speech. Over…

This PhD thesis explores the field of scene understanding using sound through artificial intelligence techniques. It addresses the challenge of extracting relevant information from sound in environments where other sensory inputs, such as vision, are limited or occluded. The work contributes novel methods and models for Acoustic Scene Classification (ASC), Sound Event Detection (SED), Unsupervised…

Distributed machine learning for Internet of Things (IoT) and cyber-physical systems (CPS) applications faces increasing demands for efficiency, privacy, and robustness. This thesis focuses on addressing these challenges through two primary approaches, i.e., fully-distributed learning algorithms and federated learning (FL) algorithms, which form the main contributions of the work. This study proposes machine learning algorithms…

The radio spectrum remains a scarce resource under increasing demand for wireless communication despite evolving technologies. Cognitive Radio (CR) addresses this by allowing secondary users (SUs) to access underutilized licensed spectrum. A key function of CR systems is spectrum sensing, which detects primary users (PUs) and identifies available spectral opportunities for secondary use. Therefore, this…

Robust signal processing and machine learning methodologies are critical for the reliable operation of modern technological systems, particularly in dynamic and uncertain environments such as the Internet of Things (IoT). However, system performance is often compromised by pervasive challenges, including structural perturbations in graph-based models, complex non-Gaussian noise in communication systems, and the structural heterogeneity…

Accurate and robust positioning remains a fundamental challenge in Global Navigation Satellite System (GNSS) navigation, especially in weak-signal, high-dynamics, interference-prone, and model-mismatched environments. Conventional two-step positioning approaches and Kalman Filter (KF)-based methods rely heavily on accurate observation models and state-space dynamics, which often degrade under practical imperfections such as multipath, interference, and structural modeling errors….

This dissertation advances generative speech enhancement by investigating both unsupervised and supervised machine learning approaches, with a focus on integrating visual information to improve robustness. The work is organized into three main contributions: The first contribution focuses on unsupervised generative speech enhancement. We explore a Bayesian framework combining variational autoencoders (VAEs) trained on clean speech…

This work provides a precise performance analysis of precoding in the asymptotic regime of the multi-user massive multiple-input multiple-output (MIMO) setting. Considering practical challenges, such precoders are typically formulated as non-linear, non-smooth optimization problems without closed-form solutions, often followed by non-linear post-processing operations. These aspects make it difficult to analyze the system behavior in multiple…

Probabilistic graphical models are a powerful concept for representing complex relations between components in systems with uncertain behavior. Stemming originally from statistical mechanics, their applications stretch across various fields such as computer vision, speech recognition, social network analysis, and many more. Often they allow for a compact formulation of practical challenges in terms of fundamental…