Semantic Similarity in Automatic Speech Recognition for Meetings

This thesis investigates the application of language models based on semantic similarity to Automatic Speech Recognition for meetings. We consider data-driven Latent Semantic Analysis based and knowledge-driven WordNet-based models. Latent Semantic Analysis based models are trained for several background domains and it is shown that all background models reduce perplexity compared to the n-gram baseline models, and some background models also significantly improve speech recognition for meetings. A new method for interpolating multiple models is introduced and the relation to cache-based models is investigated. The semantics of the models is investigated through a synonymity task. WordNet-based models are defined for different word-word similarities that use information encoded in the WordNet graph and corpus information. It is shown that these models can significantly improve over baseline random models on the task of word prediction, and that the chosen part-of-speech context is ...

Pucher, Michael — Graz University of Technology


Machine Learning For Data-Driven Signal Separation and Interference Mitigation in Radio-Frequency Communications

Single-channel source separation for radio-frequency (RF) systems is a challenging problem relevant to key applications, including wireless communications, radar, and spectrum monitoring. This thesis addresses the challenge by focusing on data-driven approaches for source separation, leveraging datasets of sample realizations when source models are not explicitly provided. To this end, deep learning techniques are employed as function approximations for source separation, with models trained using available data. Two problem abstractions are studied as benchmarks for our proposed deep-learning approaches. Through a simplified problem involving Orthogonal Frequency Division Multiplexing (OFDM), we reveal the limitations of existing deep learning solutions and suggest modifications that account for the signal modality for improved performance. Further, we study the impact of time shifts on the formulation of an optimal estimator for cyclostationary Gaussian time series, serving as a performance lower bound for evaluating data-driven methods. ...

Lee, Cheng Feng Gary — Massachusetts Institute of Technology


Online Machine Learning for Inference from Multivariate Time-series

Inference and data analysis over networks have become significant areas of research due to the increasing prevalence of interconnected systems and the growing volume of data they produce. Many of these systems generate data in the form of multivariate time series, which are collections of time series data that are observed simultaneously across multiple variables. For example, EEG measurements of the brain produce multivariate time series data that record the electrical activity of different brain regions over time. Cyber-physical systems generate multivariate time series that capture the behaviour of physical systems in response to cybernetic inputs. Similarly, financial time series reflect the dynamics of multiple financial instruments or market indices over time. Through the analysis of these time series, one can uncover important details about the behavior of the system, detect patterns, and make predictions. Therefore, designing effective methods for ...

Rohan Money — University of Agder, Norway


Predictive modelling and deep learning for quantifying human health

Machine learning and deep learning techniques have emerged as powerful tools for addressing complex challenges across diverse domains. These methodologies are powerful because they extract patterns and insights from large and complex datasets, automate decision-making processes, and continuously improve over time. They enable us to observe and quantify patterns in data that a normal human would not be able to capture, leading to deeper insights and more accurate predictions. This dissertation presents two research papers that leverage these methodologies to tackle distinct yet interconnected problems in neuroimaging and computer vision for the quantification of human health. The first investigation, "Age prediction using resting-state functional MRI," addresses the challenge of understanding brain aging. By employing the Least Absolute Shrinkage and Selection Operator (LASSO) on resting-state functional MRI (rsfMRI) data, we identify the most predictive correlations related to brain age. Our study, ...

Chang Jose — National Cheng Kung University


Signal Processing and Learning over Topological Spaces

The aim of this thesis is to introduce a variety of signal processing methodologies specifically designed to model, interpret, and learn from data structured within topological spaces. These spaces are loosely characterized as a collection of points together with a neighborhood notion among points. The methodologies and tools discussed herein hold particular relevance and utility when applied to signals defined over combinatorial topological spaces, such as cell complexes, or within metric spaces that exhibit non-trivial properties, such as Riemann manifolds with non-flat metrics. One of the primary motivations behind this research is to address and surmount the constraints encountered with traditional graph-based representations when they are employed to depict intricate systems. This thesis emphasizes the necessity to account for sophisticated, multiway, and geometry-sensitive interactions that are not adequately captured by conventional graph models. The contributions of this work include but ...

Battiloro Claudio — Sapienza University of Rome


Distributed Stochastic Optimization in Non-Differentiable and Non-Convex Environments

The first part of this dissertation considers distributed learning problems over networked agents. The general objective of distributed adaptation and learning is the solution of global, stochastic optimization problems through localized interactions and without information about the statistical properties of the data. Regularization is a useful technique to encourage or enforce structural properties on the resulting solution, such as sparsity or constraints. A substantial number of regularizers are inherently non-smooth, while many cost functions are differentiable. We propose distributed and adaptive strategies that are able to minimize aggregate sums of objectives. In doing so, we exploit the structure of the individual objectives as sums of differentiable costs and non-differentiable regularizers. The resulting algorithms are adaptive in nature and able to continuously track drifts in the problem; their recursions, however, are subject to persistent perturbations arising from the stochastic nature of ...

Vlaski, Stefan — University of California, Los Angeles


Bayesian data fusion for distributed learning

This dissertation explores the intersection of data fusion, federated learning, and Bayesian methods, with a focus on their applications in indoor localization, GNSS, and image processing. Data fusion involves integrating data and knowledge from multiple sources. It becomes essential when data is only available in a distributed fashion or when different sensors are used to infer a quantity of interest. Data fusion typically includes raw data fusion, feature fusion, and decision fusion. In this thesis, we will concentrate on feature fusion. Distributed data fusion involves merging sensor data from different sources to estimate an unknown process. Bayesian framework is often used because it can provide an optimal and explainable feature by preserving the full distribution of the unknown given the data, called posterior, over the estimated process at each agent. This allows for easy and recursive merging of sensor data ...

Peng Wu — Northeastern University


Contributions to Human Motion Modeling and Recognition using Non-intrusive Wearable Sensors

This thesis contributes to motion characterization through inertial and physiological signals captured by wearable devices and analyzed using signal processing and deep learning techniques. This research leverages the possibilities of motion analysis for three main applications: to know what physical activity a person is performing (Human Activity Recognition), to identify who is performing that motion (user identification) or know how the movement is being performed (motor anomaly detection). Most previous research has addressed human motion modeling using invasive sensors in contact with the user or intrusive sensors that modify the user’s behavior while performing an action (cameras or microphones). In this sense, wearable devices such as smartphones and smartwatches can collect motion signals from users during their daily lives in a less invasive or intrusive way. Recently, there has been an exponential increase in research focused on inertial-signal processing to ...

Gil-Martín, Manuel — Universidad Politécnica de Madrid


Clustering Large Dimensional Data via Second Order Statistics: Applications in Wireless Communications

In many modern signal processing applications, traditional machine learning and pattern recognition methods heavily rely on the having a sufficiently large amount of data samples to correctly estimate the underlying structures within complex signals. The main idea is to understand the inherent structural information and relationships embedded within the raw data, thereby enabling a wide variety of inference tasks. Nevertheless, the definition of what constitutes a sufficiently large dataset remains subjective and it is often problem-dependent. In this context, traditional learning approaches often fail to learn meaningful structures in the cases where the number of features closely matches (or even exceeds) the number of observations. These scenarios emphasize the need for tailored strategies that effectively extract meaningful structured information from these high-dimensional settings. In this thesis we address fundamental challenges posed by applying traditional machine learning techniques in large dimensional ...

Pereira, Roberto — CTTC


Interpretable Machine Learning for Machine Listening

Recent years have witnessed a significant interest in interpretable machine learning (IML) research that develops techniques to analyse machine learning (ML) models. Understanding ML models is essential to gain trust in their predictions and to improve datasets, model architectures and training techniques. The majority of effort in IML research has been in analysing models that classify images or structured data and comparatively less work exists that analyses models for other domains. This research focuses on developing novel IML methods and on extending existing methods to understand machine listening models that analyse audio. In particular, this thesis reports the results of three studies that apply three different IML methods to analyse five singing voice detection (SVD) models that predict singing voice activity in musical audio excerpts. The first study introduces SoundLIME (SLIME), a method to generate temporal, spectral or time-frequency explanations ...

Mishra, Saumitra — Queen Mary University of London


Deep Learning of GNSS Signal Detection

Global Navigation Satellite Systems (GNSS) is the de facto technology for Position, Navigation, and Timing (PNT) applications when it is available. GNSS relies on one or more satellite constellations that transmit ranging signals, which a receiver can use to self-localize. Signal acquisition is a crucial step in GNSS receivers, which is typically solved by maximizing the so-called Cross Ambiguity Function (CAF) resulting from a hypothesis testing problem. The CAF is a two-dimensional function that is related to the correlation between the received signal and a local code replica for every possible delay/Doppler pair, which is then maximized for signal detection and coarse synchronization. The outcome of this statistical process decides whether the signal from a particular satellite is present or absent in the received signal, as well as provides a rough estimate of its associated code delay and Doppler frequency, ...

Borhani Darian,Parisa — Northeastern University


Modeling of Magnetic Fields and Extended Objects for Localization Applications

The level of automation in our society is ever increasing. Technologies like self-driving cars, virtual reality, and fully autonomous robots, which all were unimaginable a few decades ago, are realizable today, and will become standard consumer products in the future. These technologies depend upon autonomous localization and situation awareness where careful processing of sensory data is required. To increase efficiency, robustness and reliability, appropriate models for these data are needed. In this thesis, such models are analyzed within three different application areas, namely (1) magnetic localization, (2) extended target tracking, and (3) autonomous learning from raw pixel information. Magnetic localization is based on one or more magnetometers measuring the induced magnetic field from magnetic objects. In this thesis we present a model for determining the position and the orientation of small magnets with an accuracy of a few millimeters. This ...

Wahlström, Niklas — Linköping University


Data-driven Speech Enhancement: from Non-negative Matrix Factorization to Deep Representation Learning

In natural listening environments, speech signals are easily distorted by variousacoustic interference, which reduces the speech quality and intelligibility of human listening; meanwhile, it makes difficult for many speech-related applications, such as automatic speech recognition (ASR). Thus, many speech enhancement (SE) algorithms have been developed in the past decades. However, most current SE algorithms are difficult to capture underlying speech information (e.g., phoneme) in the SE process. This causes it to be challenging to know what specific information is lost or interfered with in the SE process, which limits the application of enhanced speech. For instance, some SE algorithms aimed to improve human listening usually damage the ASR system. The objective of this dissertation is to develop SE algorithms that have the potential to capture various underlying speech representations (information) and improve the quality and intelligibility of noisy speech. This ...

Xiang, Yang — Aalborg University, Capturi A/S


Deep Learning for Audio Effects Modeling

Audio effects modeling is the process of emulating an audio effect unit and seeks to recreate the sound, behaviour and main perceptual features of an analog reference device. Audio effect units are analog or digital signal processing systems that transform certain characteristics of the sound source. These transformations can be linear or nonlinear, time-invariant or time-varying and with short-term and long-term memory. Most typical audio effect transformations are based on dynamics, such as compression; tone such as distortion; frequency such as equalization; and time such as artificial reverberation or modulation based audio effects. The digital simulation of these audio processors is normally done by designing mathematical models of these systems. This is often difficult because it seeks to accurately model all components within the effect unit, which usually contains mechanical elements together with nonlinear and time-varying analog electronics. Most existing ...

Martínez Ramírez, Marco A — Queen Mary University of London


Analysis and Design of Linear Classifiers for High-Dimensional, Small Sample Size Data Using Asymptotic Random Matrix Theory

Due to a variety of potential barriers to sample acquisition, many of the datasets encountered in important classification applications, ranging from tumor identification to facial recognition, are characterized by small samples of high-dimensional data. In such situations, linear classifiers are popular as they have less risk of overfitting while being faster and more interpretable than non-linear classifiers. They are also easier to understand and implement for the inexperienced practitioner. In this dissertation, several gaps in the literature regarding the analysis and design of linear classifiers for high-dimensional data are addressed using tools from the field of asymptotic Random Matrix Theory (RMT) which facilitate the derivation of limits of relevant quantities or distributions, such as the probability of misclassification of a particular classifier or the asymptotic distribution of its discriminant, in the RMT regime where both the sample size and dimensionality ...

Niyazi, Lama — King Abdullah University of Science and Technology

The current layout is optimized for mobile phones. Page previews, thumbnails, and full abstracts will remain hidden until the browser window grows in width.

The current layout is optimized for tablet devices. Page previews and some thumbnails will remain hidden until the browser window grows in width.