Reverberation consists of a complex acoustic phenomenon that occurs inside rooms. Many audio signal processing methods, addressing source localization, signal enhancement and other tasks, often assume absence of reverberation. Consequently, reverberant environments are considered challenging as state-ofthe-art methods can perform poorly. The acoustics of a room can be described using a variety of mathematical models, among which, physical models are the most complete and accurate. The use of physical models in audio signal processing methods is often non-trivial since it can lead to ill-posed inverse problems. These inverse problems require proper regularization to achieve meaningful results and involve the solution of computationally intensive large-scale optimization problems. Recently, however, sparse regularization has been applied successfully to inverse problems arising in different scientific areas. The increased computational power of modern computers and the development of new efficient optimization algorithms makes it possible ...

Modern devices such as mobile phones, tablets or smart speakers are commonly equipped with several loudspeakers and microphones. If, for instance, one employs such a device for hands-free communication applications, the signals that are reproduced by the loudspeakers are propagated through the room and are inevitably acquired by the microphones. If no processing is applied, the participants in the far-end room receive delayed reverberated replicas of their own voice, which strongly degrades both speech intelligibility and user comfort. In order to prevent that so-called acoustic echoes are transmitted back to the far-end room, acoustic echo cancelers are commonly employed. The latter make use of adaptive filtering techniques to identify the propagation paths between loudspeakers and microphones. The estimated propagation paths are then employed to compute acoustic echo estimates, which are finally subtracted from the signals acquired by the microphones. In ...

A speech signal captured by multiple microphones is often subject to a reduced intelligibility and quality due to the presence of noise and room acoustic interferences. Multi-microphone speech enhancement systems therefore aim at the suppression or cancellation of such undesired signals without substantial distortion of the speech signal. A fundamental aspect to the design of several multi-microphone speech enhancement systems is that of the spatial information which relates each microphone signal to the desired speech source. This spatial information is unknown in practice and has to be somehow estimated. Under certain conditions, however, the estimated spatial information can be inaccurate, which subsequently degrades the performance of a multi-microphone speech enhancement system. This doctoral dissertation is focused on the development and evaluation of acoustic signal processing algorithms in order to address this issue. Specifically, as opposed to conventional means of estimating ...

Multimedia consumer electronics are nowadays everywhere from teleconferencing, hands-free communications, in-car communications to smart TV applications and more. We are living in a world of telecommunication where ideal scenarios for implementing these applications are hard to find. Instead, practical implementations typically bring many problems associated to each real-life scenario. This thesis mainly focuses on two of these problems, namely, acoustic echo and acoustic feedback. On the one hand, acoustic echo cancellation (AEC) is widely used in mobile and hands-free telephony where the existence of echoes degrades the intelligibility and listening comfort. On the other hand, acoustic feedback limits the maximum amplification that can be applied in, e.g., in-car communications or in conferencing systems, before howling due to instability, appears. Even though AEC and acoustic feedback cancellation (AFC) are functional in many applications, there are still open issues. This means that ...

In today's audio production and reproduction as well as in music performance practices it has become common practice to alter reverberation artificially through electronics or electro-acoustics. For music productions, radio plays, and movie soundtracks, the sound is often captured in small studio spaces with little to no reverberation to save real estate and to ensure a controlled environment such that the artistically intended spatial impression can be added during post-production. Spatial sound reproduction systems require flexible adjustment of artificial reverberation to the diffuse sound portion to help the reconstruction of the spatial impression. Many modern performance spaces are multi-purpose, and the reverberation needs to be adjustable to the desired performance style. Employing electro-acoustic feedback, also known as Reverberation Enhancement Systems (RESs), it is possible to extend the physical to the desired reverberation. These examples demonstrate a wide range of applications ...

Compressed sensing (CS) is a recently introduced signal acquisition framework that goes against the traditional Nyquist sampling paradigm. CS demonstrates that a sparse, or compressible, signal can be acquired using a low rate acquisition process. Since noise is always present in practical data acquisition systems, sensing and reconstruction methods are developed assuming a Gaussian (light-tailed) model for the corrupting noise. However, when the underlying signal and/or the measurements are corrupted by impulsive noise, commonly employed linear sampling operators, coupled with Gaussian-derived reconstruction algorithms, fail to recover a close approximation of the signal. This dissertation develops robust sampling and reconstruction methods for sparse signals in the presence of impulsive noise. To achieve this objective, we make use of robust statistics theory to develop appropriate methods addressing the problem of impulsive noise in CS systems. We develop a generalized Cauchy distribution (GCD) ...

Given the widespread use of miniaturized audio interfaces, echo control systems are faced with increasing challenges to address a large variety of acoustic conditions observed by such interfaces. This motivates the use of sophisticated machine learning-based techniques to overcome the limitations of conventional methods. The contributions in this thesis can be outlined by decomposing the task of nonlinear acoustic echo control into two subtasks: Nonlinear Acoustic Echo Cancellation (NAEC) and Acoustic Echo Suppression (AES). In particular, by formulating the single-channel NAEC model-adaptation task as a Bayesian recursive filtering problem, an evolutionary resampling strategy for particle filtering is proposed. The resulting Elitist Resampling Particle Filter (ERPF) is shown experimentally to be an efficient and high-performing approach that can be extended to address challenging conditions such as non-stationary interferers. The fundamental problem of nonlinear model design is addressed by proposing a novel ...

In typical speech communication applications, such as hands-free mobile telephony, voice-controlled systems and hearing aids, the recorded microphone signals are corrupted by background noise, room reverberation and far-end echo signals. This signal degradation can lead to total unintelligibility of the speech signal and decreases the performance of automatic speech recognition systems. In this thesis several multi-microphone noise reduction and dereverberation techniques are developed. In Part I we present a Generalised Singular Value Decomposition (GSVD) based optimal filtering technique for enhancing multi-microphone speech signals which are degraded by additive coloured noise. Several techniques are presented for reducing the computational complexity and we show that the GSVD-based optimal filtering technique can be integrated into a `Generalised Sidelobe Canceller' type structure. Simulations show that the GSVD-based optimal filtering technique achieves a larger signal-to-noise ratio improvement than standard fixed and adaptive beamforming techniques and ...

As many machine learning and signal processing problems are fundamentally nonconvex and too expensive/difficult to be convexified, my research is focused on understanding the optimization landscapes of their fundamentally nonconvex formulations. After understanding their optimization landscapes, we can develop optimization algorithms to efficiently navigate these optimization landscapes and achieve the global optimality convergence. So, the main theme of this thesis would be optimization, with an emphasis on nonconvex optimization and algorithmic developments for these popular optimization problems. This thesis can be conceptually divided into four parts: Part 1: Convex Optimization. In the first part, we apply convex relaxations to several popular nonconvex problems in signal processing and machine learning (e.g. line spectral estimation problem and tensor decomposition problem) and prove that the solving the new convex relaxation problems is guaranteed to achieve the globally optimal solutions of their original nonconvex ...

The abundance of large and heterogeneous systems is rendering contemporary data more pervasive, intricate, and with a non-regular structure. With classical techniques facing troubles to deal with the irregular (non-Euclidean) domain where the signals are defined, a popular approach at the heart of graph signal processing (GSP) is to: (i) represent the underlying support via a graph and (ii) exploit the topology of this graph to process the signals at hand. In addition to the irregular structure of the signals, another critical limitation is that the observed data is prone to the presence of perturbations, which, in the context of GSP, may affect not only the observed signals but also the topology of the supporting graph. Ignoring the presence of perturbations, along with the couplings between the errors in the signal and the errors in their support, can drastically hinder ...

In this work, a novel set of robust watermark-based error concealment (WEC) algorithms are proposed. Watermarking is used to introduce redundancy to the transmitted data with little or no increase in its bit rate during transmission. The proposed algorithms involve generating a low resolution version of a video frame and seamlessly embedding it as a watermark in the frame itself during encoding. At the receiver, the watermark is extracted from the reconstructed frame and the lost information is recovered using the extracted watermark signal, thus enhancing its perceptual quality. Three DCT-based spread spectrum watermark embedding techniques are presented in this work. The first technique uses a multiplicative Gaussian pseudo-noise with a pre-defined spreading gain and fixed chip rate. The second one is its adaptively scaled version and the third technique uses informed watermarking. Two versions of the low resolution reference, ...

Reverberation is the sum of reflected sound waves and is present in any conventional room. Speech communication devices such as mobile phones in hands-free mode, tablets, smart TVs, teleconferencing systems, hearing aids, voice-controlled systems, etc. use one or more microphones to pick up the desired speech signals. When the microphones are not in the proximity of the desired source, strong reverberation and noise can degrade the signal quality at the microphones and can impair the intelligibility and the performance of automatic speech recognizers. Therefore, it is a highly demanded task to process the microphone signals such that reverberation and noise are reduced. The process of reducing or removing reverberation from recorded signals is called dereverberation. As dereverberation is usually a completely blind problem, where the only available information are the microphone signals, and as the acoustic scenario can be non-stationary, ...

Ill-posed inverse problems appear in many signal and image processing applications, such as deblurring, super-resolution and compressed sensing. The common approach to address them is to design a specific algorithm, or recently, a specific deep neural network, for each problem. Both signal processing and machine learning tactics have drawbacks: traditional reconstruction strategies exhibit limited performance for complex signals, such as natural images, due to the hardness of their mathematical modeling; while modern works that circumvent signal modeling by training deep convolutional neural networks (CNNs) suffer from a huge performance drop when the observation model used in training is inexact. In this work, we develop and analyze reconstruction algorithms that are not restricted to a specific signal model and are able to handle different observation models. Our main contributions include: (a) We generalize the popular sparsity-based CoSaMP algorithm to any signal ...

Digital subscriber line (DSL) technology is one of the fastest growing broadband internet access media. Whereas asymmetric DSL (ADSL) already offers data rates of a few megabits per second, next-generation ADSL2+ and VDSL promise even higher bit rates to support so-called triple play (high-quality video, voice and high-speed data). The use of a large bandwidth over the phone line (up to 12 MHz for VDSL) induces impairments, such as severe channel distortion, echo, narrow-band radiofrequency interference (RFI) and crosstalk from other DSL systems. DSL communication makes use of so-called discrete multitone (DMT) modulation, supplemented with advanced digital signal processing algorithms, to tackle these impairments and serve a maximum number of customers. In this thesis, we focus on channel equalization and RFI mitigation algorithms that outperform existing algorithms in terms of bit rate. DMT equalization is typically done by means of ...

This thesis is related to the field of Sound Source Separation (SSS). It addresses the development and evaluation of these techniques for their application in the resynthesis of high-realism sound scenes by means of Wave Field Synthesis (WFS). Because the vast majority of audio recordings are preserved in two-channel stereo format, special up-converters are required to use advanced spatial audio reproduction formats, such as WFS. This is due to the fact that WFS needs the original source signals to be available, in order to accurately synthesize the acoustic field inside an extended listening area. Thus, an object-based mixing is required. Source separation problems in digital signal processing are those in which several signals have been mixed together and the objective is to find out what the original signals were. Therefore, SSS algorithms can be applied to existing two-channel mixtures to ...