Showing papers in "IEEE Signal Processing Magazine in 2015"
TL;DR: Benefiting from the power of multilinear algebra as their mathematical backbone, data analysis techniques using tensor decompositions are shown to have great flexibility in the choice of constraints which match data properties and extract more general latent components in the data than matrix-based methods.
Abstract: The widespread use of multisensor technology and the emergence of big data sets have highlighted the limitations of standard flat-view matrix models and the necessity to move toward more versatile data analysis tools. We show that higher-order tensors (i.e., multiway arrays) enable such a fundamental paradigm shift toward models that are essentially polynomial, the uniqueness of which, unlike the matrix methods, is guaranteed under very mild and natural conditions. Benefiting from the power of multilinear algebra as their mathematical backbone, data analysis techniques using tensor decompositions are shown to have great flexibility in the choice of constraints which match data properties and extract more general latent components in the data than matrix-based methods.
1,250 citations
TL;DR: A survey of domain adaptation methods for visual recognition discusses the merits and drawbacks of existing domain adaptation approaches and identifies promising avenues for research in this rapidly evolving field.
Abstract: In pattern recognition and computer vision, one is often faced with scenarios where the training data used to learn a model have different distribution from the data on which the model is applied. Regardless of the cause, any distributional change that occurs after learning a classifier can degrade its performance at test time. Domain adaptation tries to mitigate this degradation. In this article, we provide a survey of domain adaptation methods for visual recognition. We discuss the merits and drawbacks of existing domain adaptation approaches and identify promising avenues for research in this rapidly evolving field.
871 citations
TL;DR: The goal is to describe the current state of the art in this area, identify challenges, and suggest future directions and areas where signal processing methods can have a large impact on optical imaging and on the world of imaging at large.
Abstract: i»?The problem of phase retrieval, i.e., the recovery of a function given the magnitude of its Fourier transform, arises in various fields of science and engineering, including electron microscopy, crystallography, astronomy, and optical imaging. Exploring phase retrieval in optical settings, specifically when the light originates from a laser, is natural since optical detection devices [e.g., charge-coupled device (CCD) cameras, photosensitive films, and the human eye] cannot measure the phase of a light wave. This is because, generally, optical measurement devices that rely on converting photons to electrons (current) do not allow for direct recording of the phase: the electromagnetic field oscillates at rates of ~1015âHz, which no electronic measurement device can follow. Indeed, optical measurement/detection systems measure the photon flux, which is proportional to the magnitude squared of the field, not the phase. Consequently, measuring the phase of optical waves (electromagnetic fields oscillating at 1015âHz and higher) involves additional complexity, typically by requiring interference with another known field, in the process of holography.
869 citations
TL;DR: A comparative study of human versus machine speaker recognition is concluded, with an emphasis on prominent speaker-modeling techniques that have emerged in the last decade for automatic systems.
Abstract: Identifying a person by his or her voice is an important human trait most take for granted in natural human-to-human interaction/communication. Speaking to someone over the telephone usually begins by identifying who is speaking and, at least in cases of familiar speakers, a subjective verification by the listener that the identity is correct and the conversation can proceed. Automatic speaker-recognition systems have emerged as an important means of verifying identity in many e-commerce applications as well as in general business interactions, forensics, and law enforcement. Human experts trained in forensic speaker recognition can perform this task even better by examining a set of acoustic, prosodic, and linguistic characteristics of speech in a general approach referred to as structured listening. Techniques in forensic speaker recognition have been developed for many years by forensic speech scientists and linguists to help reduce any potential bias or preconceived understanding as to the validity of an unknown audio sample and a reference template from a potential suspect. Experienced researchers in signal processing and machine learning continue to develop automatic algorithms to effectively perform speaker recognition?with ever-improving performance?to the point where automatic systems start to perform on par with human listeners. In this article, we review the literature on speaker recognition by machines and humans, with an emphasis on prominent speaker-modeling techniques that have emerged in the last decade for automatic systems. We discuss different aspects of automatic systems, including voice-activity detection (VAD), features, speaker models, standard evaluation data sets, and performance metrics. Human speaker recognition is discussed in two parts?the first part involves forensic speaker-recognition methods, and the second illustrates how a na?ve listener performs this task from a neuroscience perspective. We conclude this review with a comparative study of human versus machine speaker recognition and attempt to point out strengths and weaknesses of each.
554 citations
TL;DR: The state of the art of resampling methods was reviewed and the methods were classified and their properties were compared in the framework of the proposed classifications to provide guidelines to practitioners and researchers.
Abstract: Two decades ago, with the publication of [1], we witnessed the rebirth of particle filtering (PF) as a methodology for sequential signal processing. Since then, PF has become very popular because of its ability to process observations represented by nonlinear state-space models where the noises of the model can be non-Gaussian. This methodology has been adopted in various fields, including finance, geophysical systems, wireless communications, control, navigation and tracking, and robotics [2]. The popularity of PF has also spurred the publication of several review articles [2]?[6].
409 citations
TL;DR: The fundamental properties of EDMs, such as rank or (non)definiteness, are reviewed, and it is shown how the various EDM properties can be used to design algorithms for completing and denoising distance data.
Abstract: Euclidean distance matrices (EDMs) are matrices of the squared distances between points. The definition is deceivingly simple; thanks to their many useful properties, they have found applications in psychometrics, crystallography, machine learning, wireless sensor networks, acoustics, and more. Despite the usefulness of EDMs, they seem to be insufficiently known in the signal processing community. Our goal is to rectify this mishap in a concise tutorial. We review the fundamental properties of EDMs, such as rank or (non)definiteness, and show how the various EDM properties can be used to design algorithms for completing and denoising distance data. Along the way, we demonstrate applications to microphone position calibration, ultrasound tomography, room reconstruction from echoes, and phase retrieval. By spelling out the essential algorithms, we hope to fast-track the readers in applying EDMs to their own problems. The code for all of the described algorithms and to generate the figures in the article is available online at http://lcav.epfl.ch/ivan.dokmanic. Finally, we suggest directions for further research.
383 citations
TL;DR: An account of the state of the art in acoustic scene classification (ASC), the task of classifying environments from the sounds they produce, and a range of different algorithms submitted for a data challenge to provide a general and fair benchmark for ASC techniques.
Abstract: In this article, we present an account of the state of the art in acoustic scene classification (ASC), the task of classifying environments from the sounds they produce. Starting from a historical review of previous research in this area, we define a general framework for ASC and present different implementations of its components. We then describe a range of different algorithms submitted for a data challenge that was held to provide a general and fair benchmark for ASC techniques. The data set recorded for this purpose is presented along with the performance metrics that are used to evaluate the algorithms and statistical significance tests to compare the submitted methods.
352 citations
TL;DR: An overview of various cancelable biometric schemes for biometric template protection is provided and the merits and drawbacks of available cancelableBiometric systems are discussed and promising avenues of research are identified.
Abstract: Recent years have seen an exponential growth in the use of various biometric technologies for trusted automatic recognition of humans With the rapid adaptation of biometric systems, there is a growing concern that biometric technologies may compromise the privacy and anonymity of individuals Unlike credit cards and passwords, which can be revoked and reissued when compromised, biometrics are permanently associated with a user and cannot be replaced To prevent the theft of biometric patterns, it is desirable to modify them through revocable and noninvertible transformations to produce cancelable biometric templates In this article, we provide an overview of various cancelable biometric schemes for biometric template protection We discuss the merits and drawbacks of available cancelable biometric systems and identify promising avenues of research in this rapidly evolving field
320 citations
TL;DR: In this article, the authors present the principles of primal?dual approaches while providing an overview of the numerical methods that have been proposed in different contexts, including convex analysis, discrete optimization, parallel processing, and nonsmooth optimization with an emphasis on sparsity issues.
Abstract: Optimization methods are at the core of many problems in signal/image processing, computer vision, and machine learning. For a long time, it has been recognized that looking at the dual of an optimization problem may drastically simplify its solution. However, deriving efficient strategies that jointly bring into play the primal and dual problems is a more recent idea that has generated many important new contributions in recent years. These novel developments are grounded in the recent advances in convex analysis, discrete optimization, parallel processing, and nonsmooth optimization with an emphasis on sparsity issues. In this article, we aim to present the principles of primal?dual approaches while providing an overview of the numerical methods that have been proposed in different contexts. Last but not least, primal?dual methods lead to algorithms that are easily parallelizable. Today, such parallel algorithms are becoming increasingly important for efficiently handling high-dimensional problems.
316 citations
TL;DR: The objective of this work is to analyze the factors contributing to this performance divide and highlight promising research directions to bridge this gap and cross the chasm between theory and practice in biometric template protection.
Abstract: Biometric recognition is an integral component of modern identity management and access control systems. Due to the strong and permanent link between individuals and their biometric traits, exposure of enrolled users? biometric information to adversaries can seriously compromise biometric system security and user privacy. Numerous techniques have been proposed for biometric template protection over the last 20 years. While these techniques are theoretically sound, they seldom guarantee the desired noninvertibility, revocability, and nonlinkability properties without significantly degrading the recognition performance. The objective of this work is to analyze the factors contributing to this performance divide and highlight promising research directions to bridge this gap. The design of invariant biometric representations remains a fundamental problem, despite recent attempts to address this issue through feature adaptation schemes. The difficulty in estimating the statistical distribution of biometric features not only hinders the development of better template protection algorithms but also diminishes the ability to quantify the noninvertibility and nonlinkability of existing algorithms. Finally, achieving nonlinkability without the use of external secrets (e.g., passwords) continues to be a challenging proposition. Further research on the above issues is required to cross the chasm between theory and practice in biometric ?template protection.
265 citations
TL;DR: This work focuses on single-channel speech enhancement algorithms which rely on spectrotemporal properties, and can be employed when the miniaturization of devices only allows for using a single microphone.
Abstract: With the advancement of technology, both assisted listening devices and speech communication devices are becoming more portable and also more frequently used. As a consequence, users of devices such as hearing aids, cochlear implants, and mobile telephones, expect their devices to work robustly anywhere and at any time. This holds in particular for challenging noisy environments like a cafeteria, a restaurant, a subway, a factory, or in traffic. One way to making assisted listening devices robust to noise is to apply speech enhancement algorithms. To improve the corrupted speech, spatial diversity can be exploited by a constructive combination of microphone signals (so-called beamforming), and by exploiting the different spectro?temporal properties of speech and noise. Here, we focus on single-channel speech enhancement algorithms which rely on spectrotemporal properties. On the one hand, these algorithms can be employed when the miniaturization of devices only allows for using a single microphone. On the other hand, when multiple microphones are available, single-channel algorithms can be employed as a postprocessor at the output of a beamformer. To exploit the short-term stationary properties of natural sounds, many of these approaches process the signal in a time-frequency representation, most frequently the short-time discrete Fourier transform (STFT) domain. In this domain, the coefficients of the signal are complex-valued, and can therefore be represented by their absolute value (referred to in the literature both as STFT magnitude and STFT amplitude) and their phase. While the modeling and processing of the STFT magnitude has been the center of interest in the past three decades, phase has been largely ignored.
TL;DR: In this article, Hidden Markov Models (HMMs) and Gaussian Mixture Models (GMMs) are used for generating low-level speech waveforms from high-level symbolic inputs via intermediate acoustic feature sequences.
Abstract: Hidden Markov models (HMMs) and Gaussian mixture models (GMMs) are the two most common types of acoustic models used in statistical parametric approaches for generating low-level speech waveforms from high-level symbolic inputs via intermediate acoustic feature sequences. However, these models have their limitations in representing complex, nonlinear relationships between the speech generation inputs and the acoustic features. Inspired by the intrinsically hierarchical process of human speech production and by the successful application of deep neural networks (DNNs) to automatic speech recognition (ASR), deep learning techniques have also been applied successfully to speech generation, as reported in recent literature.
TL;DR: The rate at which phenotypes are extracted in the field or in the lab is not matching the speed of genotyping and is creating a bottleneck, which needs to be addressed.
Abstract: Plant phenotyping is the identification of effects on the phenotype (i.e., the plant appearance and performance) as a result of genotype differences (i.e., differences in the genetic code) and the environmental conditions to which a plant has been exposed [1]?[3]. According to the Food and Agriculture Organization of the United Nations, large-scale experiments in plant phenotyping are a key factor in meeting the agricultural needs of the future to feed the world and provide biomass for energy, while using less water, land, and fertilizer under a constantly evolving environment due to climate change. Working on model plants (such as Arabidopsis), combined with remarkable advances in genotyping, has revolutionized our understanding of biology but has accelerated the need for precision and automation in phenotyping, favoring approaches that provide quantifiable phenotypic information that could be better used to link and find associations in the genotype [4]. While early on, the collection of phenotypes was manual, currently noninvasive, imaging-based methods are increasingly being utilized [5], [6]. However, the rate at which phenotypes are extracted in the field or in the lab is not matching the speed of genotyping and is creating a bottleneck [1].
TL;DR: This tutorial article presents an introduction to spoofing and antispoofing research, describes the vulnerabilities, presents an evaluation methodology for the assessment of spoofs and countermeasures, and outlines research priorities for the future.
Abstract: Biometrics already form a significant component of current and emerging identification technologies. Biometrics systems aim to determine or verify the identity of an individual from their behavioral and/or biological characteristics. Despite significant progress, some biometric systems fail to meet the multitude of stringent security and robustness requirements to support their deployment in some practical scenarios. Among current concerns are vulnerabilities to spoofing?persons who masquerade as others to gain illegitimate accesses to protected data, services, or facilities. While the study of spoofing, or rather antispoofing, has attracted growing interest in recent years, the problem is far from being solved and will require far greater attention in the coming years. This tutorial article presents an introduction to spoofing and antispoofing research. It describes the vulnerabilities, presents an evaluation methodology for the assessment of spoofing and countermeasures, and outlines research priorities for the future.
TL;DR: For people with normal hearing, assisted listening devices (ALDs) mainly aim to achieve hearing protection or increase listening comfort; however, for hearing-impaired individuals, as the most prominent user group so far, further progress of assisted listening technology is crucial for better inclusion into the authors' world of pervasive acoustic communication.
Abstract: In everyday environments, we are frequently immersed by unwanted acoustic noise and interference while we want to listen to acoustic signals, most often speech. Technology for assisted listening is then desired to increase the efficiency of speech communication, reduce listener fatigue, or just allow for enjoying undisturbed sounds (e.g., music). For people with normal hearing, assisted listening devices (ALDs) mainly aim to achieve hearing protection or increase listening comfort; however, for hearing-impaired individuals, as the most prominent user group so far, further progress of assisted listening technology is crucial for better inclusion into our world of pervasive acoustic communication.
TL;DR: Flexible spectrum use and cognitive radio technologies provide an approach to alleviating the lack of availability of radio spectrum by allowing for secondary spectrum use while the spectrum is underutilized by its primary licensed users.
Abstract: The lack of availability of radio spectrum for wireless communication purposes is becoming a serious problem as more wireless systems and services are being developed and operate in crowded spectral bands. The scarcity of useful radio spectrum is mainly due to the static allocation and rigid regulation of the spectrum use rather than the spectrum being actually fully in use. Flexible spectrum use and cognitive radio technologies provide an approach to alleviating this problem by allowing for secondary spectrum use while the spectrum is underutilized by its primary licensed users. Idle spectrum is a time?frequency?location varying resource. It is a resource that also depends on the relative locations of the primary and secondary receivers and transmitters as well as the instantaneous propagation conditions. By acquiring awareness about the current radio environment and the other spectrum users, cognitive radios can more efficiently exploit idle spectrum and manage interference. Doing so requires a means to explore the spectrum to identify high-quality and persistent local spectral resources and access and share them among a number of users while strictly controlling the interference caused to others, in particular, licensed primary users (PUs). Situational awareness about the state of the spectrum allows for optimal exploitation of underutilized spectrum. For example, idle subbands may be allocated, and waveform parameters may be chosen to maximize the sum-rate for the cognitive users while making sure no harmful interference is caused to the other users of the spectrum.
TL;DR: A wave-domain sound field representation and active room compensation for sound pressure control over a region of space is introduced and a unified framework is presented to compare two state-of-the-art sound control techniques.
Abstract: Sound rendering is increasingly being required to extend over certain regions of space for multiple listeners, known as personal sound zones, with minimum interference to listeners in other regions. In this article, we present a systematic overview of the major challenges that have to be dealt with for multizone sound control in a room. Sound control over multiple zones is formulated as an optimization problem, and a unified framework is presented to compare two state-of-the-art sound control techniques. While conventional techniques have been focusing on point-to-point audio processing, we introduce a wave-domain sound field representation and active room compensation for sound pressure control over a region of space. The design of directional loudspeakers is presented and the advantages of using arrays of directional sources are illustrated for sound reproduction, such as better control of sound fields over wide areas and reduced total number of loudspeaker units, thus making it particularly suitable for establishing personal sound zones.
TL;DR: There is a niche for image analysis methods that can automate some aspects of this analysis of tissue sections, e.g., discovering new disease markers from hundreds of whole-slide images (WSIs) or precisely quantifying tissues within a tumor.
Abstract: Histology is the microscopic inspection of plant or animal tissue. It is a critical component in diagnostic medicine and a tool for studying the pathogenesis and biology of processes such as cancer and embryogenesis. Tissue processing for histology has become increasingly automated, drastically increasing the speed at which histology labs can produce tissue slides for viewing. Another trend is the digitization of these slides, allowing them to be viewed on a computer rather than through a microscope. Despite these changes, much of the routine analysis of tissue sections remains a painstaking, manual task that can only be completed by highly trained pathologists at a high cost per hour. There is, therefore, a niche for image analysis methods that can automate some aspects of this analysis. These methods could also automate tasks that are prohibitively time-consuming for humans, e.g., discovering new disease markers from hundreds of whole-slide images (WSIs) or precisely quantifying tissues within a tumor.
TL;DR: An overview of 12 existing objective speech quality and intelligibility prediction tools is presented and recommendations are given for suggested uses of the different tools under specific environmental and processing conditions.
Abstract: This article presents an overview of 12 existing objective speech quality and intelligibility prediction tools. Two classes of algorithms are presented?intrusive and nonintrusive?with the former requiring the use of a reference signal, while the latter does not. Investigated metrics include both those developed for normal hearing (NH) listeners, as well as those tailored particularly for hearing impaired (HI) listeners who are users of assistive listening devices [i.e., hearing aids (HAs) and cochlear implants (CIs)]. Representative examples of those optimized for HI listeners include the speech-to-reverberation modulation energy ratio (SRMR), tailored to HAs (SRMR-HA) and to CIs (SRMR-CI); the modulation spectrum area (ModA); the HA speech quality (HASQI) and perception indices (HASPI); and the perception-model-based quality prediction method for hearing impairments (PEMO-Q-HI). The objective metrics are tested on three subjectively rated speech data sets covering reverberation-alone, noise-alone, and reverberation-plus-noise degradation conditions, as well as degradations resultant from nonlinear frequency compression and different speech enhancement strategies. The advantages and limitations of each measure are highlighted and recommendations are given for suggested uses of the different tools under specific environmental and processing conditions.
TL;DR: PigeoNET is shown to be capable of attributing previously unseen artworks to the actual artists with an accuracy of more than 70% and represents a fruitful approach for the future of computer-supported examination of artworks.
Abstract: Author attribution through the recognition of visual characteristics is a commonly used approach by art experts. By studying a vast number of artworks, art experts acquire the ability to recognize the unique characteristics of artists. In this article, we present an approach that uses the same principles to discover the characteristic features that determine an artist?s touch. By training a convolutional neural network (PigeoNET) on a large collection of digitized artworks to perform the task of automatic artist attribution, the network is encouraged to discover artist-specific visual features. The trained network is shown to be capable of attributing previously unseen artworks to the actual artists with an accuracy of more than 70%. In addition, the trained network provides fine-grained information about the artist-specific characteristics of spatial regions within the artworks. We demonstrate this ability by means of a single artwork that combines characteristics of two closely collaborating artists. PigeoNET generates a visualization that indicates for each location on the artwork who is the most likely artist to have contributed to the visual characteristics at that location. We conclude that PigeoNET represents a fruitful approach for the future of computer-supported examination of artworks.
TL;DR: Progress in sound coding for CIs is reviewed and the current commercially most-used signal processing schemes are discussed, as well as recent developments in coding strategies that aim to improve auditory perception.
Abstract: Cochlear implantation is a life-changing intervention for people with a severe hearing impairment [1]. For most cochlear implant (CI) users, speech intelligibility is satisfactory in quiet environments. Although modern CIs provide up to 22 stimulation channels, information transfer is still limited for the perception of fine spectrotemporal details in many types of sound. These details contribute to the perception of music and speech in common listening situations, such as where background noise is present. Over the past several decades, many different sound processing strategies have been developed to provide more details about acoustic signals to CI users. In this article, progress in sound coding for CIs is reviewed. Starting from a basic strategy, the current commercially most-used signal processing schemes are discussed, as well as recent developments in coding strategies that aim to improve auditory perception. This article focuses particularly on the stimulation strategies, which convert sound signals into patterns of nerve stimulation. The neurophysiological rationale behind some of these strategies is discussed and aspects of CI performance that require further improvement are identified.
TL;DR: Making microscopy more quantitative brings important scientific benefits in the form of improved performance and reproducibility and computerized extraction of quantitative information out of the rapidly expanding amount of acquired data remains a major challenge.
Abstract: In recent years, there has been an increasing interest in getting a proper quantitative understanding of cellular and molecular processes [1], [2]. One of the major challenges of current biomedical research is to characterize not only the spatial organization of these complex systems but also their spatiotemporal relationships [3], [4]. Microscopy has matured to the point that it enables sensitive time-lapse imaging of cells in vivo and even of single molecules [5], [6]. Making microscopy more quantitative brings important scientific benefits in the form of improved performance and reproducibility. This has been fostered by the development of technological achievements such as high-throughput microscopy. A direct consequence is that the size and complexity of image data are increasing. Time-lapse experiments commonly generate hundreds to thousands of images, each containing hundreds of objects to be analyzed [7]. These data often cannot be analyzed manually because the manpower required would be too extensive, which calls for automated methods for the analysis of biomedical images. Such computerized extraction of quantitative information out of the rapidly expanding amount of acquired data remains a major challenge. The development of the related algorithms is nontrivial and is one of the most active fronts in the new field of bioimage informatics [8]?[11]. Segmenting thousands of individual biological objects and tracking them over time is remarkably difficult. A typical algorithm will need to be tuned to the imaging modality and will have to cope with the fact that cells can be tightly packed and may appear in various configurations, making them difficult to segregate.
TL;DR: Systems employing biometric traits for people authentication and identification are witnessing growing popularity due to the unique and indissoluble link between any individual and his/her biometric characters, and biometric templates are increasingly used for border monitoring, access control, membership verification, and so on.
Abstract: Systems employing biometric traits for people authentication and identification are witnessing growing popularity due to the unique and indissoluble link between any individual and his/her biometric characters. For this reason, biometric templates are increasingly used for border monitoring, access control, membership verification, and so on. When employed to replace passwords, biometrics have the added advantage that they do not need to be memorized and are relatively hard to steal. Nonetheless, unlike conventional security mechanisms such as passwords, biometric data are inherent parts of a person?s body and cannot be replaced if they are compromised. Even worse, compromised biometric data can be used to have access to sensitive information and to impersonate the victim for malicious purposes. For the same reason, biometric leakage in a given system can seriously jeopardize the security of other systems based on the same biometrics. A further problem associated with the use of biometric traits is that, due to their uniqueness, the privacy of their owner is put at risk. Geographical position, movements, habits, and even personal beliefs can be tracked by observing when and where the biometric traits of an individual are used to identify him/her.
TL;DR: A taxonomy of the algorithms based on methodological considerations, a discussion of the identifiability and convergence properties, advantages, drawbacks, and application domains of various techniques, and an illustration of the performance of seven selected methods on identical data sets are proposed.
Abstract: A number of application areas such as biomedical engineering require solving an underdetermined linear inverse problem. In such a case, it is necessary to make assumptions on the sources to restore identifiability. This problem is encountered in brain-source imaging when identifying the source signals from noisy electroencephalographic or magnetoencephalographic measurements. This inverse problem has been widely studied during recent decades, giving rise to an impressive number of methods using different priors. Nevertheless, a thorough study of the latter, including especially sparse and tensor-based approaches, is still missing. In this article, we propose 1) a taxonomy of the algorithms based on methodological considerations; 2) a discussion of the identifiability and convergence properties, advantages, drawbacks, and application domains of various techniques; and 3) an illustration of the performance of seven selected methods on identical data sets. Directions for future research in the area of biomedical imaging are eventually provided.
TL;DR: Previous work on biometric security under a recent framework proposed in the field of adversarial machine learning is reviewed to highlight novel insights on the security of biometric systems when operating in the presence of intelligent and adaptive attackers that manipulate data to compromise normal system operation.
Abstract: In this article, we review previous work on biometric security under a recent framework proposed in the field of adversarial machine learning. This allows us to highlight novel insights on the security of biometric systems when operating in the presence of intelligent and adaptive attackers that manipulate data to compromise normal system operation. We show how this framework enables the categorization of known and novel vulnerabilities of biometric recognition systems, along with the corresponding attacks, countermeasures, and defense mechanisms. We report two application examples, respectively showing how to fabricate a more effective face spoofing attack, and how to counter an attack that exploits an unknown vulnerability of an adaptive face-recognition system to compromise its face templates.
TL;DR: Many classes of data are composed as constructive combinations of parts that do not result in subtraction or diminishment of any of the parts, and these models are referred to as compositional models.
Abstract: Many classes of data are composed as constructive combinations of parts. By constructive combination, we mean additive combination that does not result in subtraction or diminishment of any of the parts. We will refer to such data as compositional data. Typical examples include population or counts data, where the total count of a population is obtained as the sum of counts of subpopulations. To characterize such data, various mathematical models have been developed in the literature. These models, in conformance with the nature of the data, represent them as nonnegative linear combinations of parts, which themselves are also nonnegative to ensure that such a combination does not result in subtraction or diminishment. We will refer to such models as compositional models.
TL;DR: This tutorial article presents signal processing techniques to tackle the challenges to assist human listening in multimedia and virtual reality applications.
Abstract: With the strong growth of assistive and personal listening devices, natural sound rendering over headphones is becoming a necessity for prolonged listening in multimedia and virtual reality applications. The aim of natural sound rendering is to naturally recreate the sound scenes with the spatial and timbral quality as natural as possible, so as to achieve a truly immersive listening experience. However, rendering natural sound over headphones encounters many challenges. This tutorial article presents signal processing techniques to tackle these challenges to assist human listening.
TL;DR: The goal of this article is to present a critical survey of the existing papers and works relating to precipitation monitoring to multidimensional signal processing, and emphasize the works relating this topic to multi-dimensional signal processing.
Abstract: Accurate measurements of precipitation are essential for many applications, ranging from flash-flood warnings to water resource management. However, the accuracy of the existing tools is limited by various technical and practical reasons. Percipitation monitoring has traditionally been known to rely on gauges, weather radars, and satellites. Recently, a new approach has begun to be examined, the usage of commercial wireless communication networks (CWCNs), which enjoys the lack of any need for deployment procedures or costs, and which is already widely spread across countries.
TL;DR: Parametric spatial sound processing has been around for two decades and provides a flexible and efficient solution to capture, code, and transmit, as well as manipulate and reproduce spatial sounds.
Abstract: Flexible and efficient spatial sound acquisition and subsequent processing are of paramount importance in communication and assisted listening devices such as mobile phones, hearing aids, smart TVs, and emerging wearable devices (e.g., smart watches and glasses). In application scenarios where the number of sound sources quickly varies, sources move, and nonstationary noise and reverberation are commonly encountered, it remains a challenge to capture sounds in such a way that they can be reproduced with a high and invariable sound quality. In addition, the objective in terms of what needs to be captured, and how it should be reproduced, depends on the application and on the user?s preferences. Parametric spatial sound processing has been around for two decades and provides a flexible and efficient solution to capture, code, and transmit, as well as manipulate and reproduce spatial sounds.
TL;DR: It is not difficult to predict that, in the near future, a headset will be a ?
Abstract: Historically, headphones have mainly been used for analytic listening in music production and in homes. During the last decade, with the boom of dedicated music players and mobile phones, the everyday use of light headphones has become highly popular. Current headphones are also paving the way for more sophisticated assisted listening devices. Today, active noise control (ANC), equalization techniques, and a hear-through function are already a standard part of many headphones that people commonly use while traveling. It is not difficult to predict that, in the near future, a headset will be a ?hearing aid for those with normal hearing,? which can improve listening conditions for example in a noisy environment.