By Topic

# IEEE Signal Processing Letters

## Filter Results

Displaying Results 1 - 25 of 31
• ### Front Cover

Publication Year: 2013, Page(s): C1
| PDF (319 KB)
• ### IEEE Signal Processing Letters publication information

Publication Year: 2013, Page(s): C2
| PDF (130 KB)

Publication Year: 2013, Page(s):191 - 192
| PDF (165 KB)
• ### Approximating the KLT by Maximizing the Sum of Fourth-Order Moments

Publication Year: 2013, Page(s):193 - 196
| | PDF (1031 KB) | HTML

In this letter, a novel approach to approximate calculation of Karhunen-Loève transform (KLT) is proposed. It is proved that with the practical assumptions the maximization of the sum of fourth-order moments of random variables in the domain of orthonormal transform leads to any permuted KLT. On the basis of theoretical results, we derive and formulate the gradient method of adaptation of ... View full abstract»

• ### Unsupervised Speech Activity Detection Using Voicing Measures and Perceptual Spectral Flux

Publication Year: 2013, Page(s):197 - 200
Cited by:  Papers (35)
| | PDF (697 KB) | HTML

Effective speech activity detection (SAD) is a necessary first step for robust speech applications. In this letter, we propose a robust and unsupervised SAD solution that leverages four different speech voicing measures combined with a perceptual spectral flux feature, for audio-based surveillance and monitoring applications. Effectiveness of the proposed technique is evaluated and compared agains... View full abstract»

• ### Speech Recognition Using Long-Span Temporal Patterns in a Deep Network Model

Publication Year: 2013, Page(s):201 - 204
Cited by:  Papers (13)
| | PDF (423 KB) | HTML

In recent years, there has been a renewed interest in the use of artificial neural networks (ANNs) for speech applications, and it seems that a new trend to move the speech technology forward has begun. Two main contributions have triggered such a new trend: 1) a major advance has been made in training the weights in deep neural networks (DNNs), and a pre-trained deep neural network hidden Markov ... View full abstract»

• ### Prior Knowledge Optimum Understanding by Means of Oblique Projectors and Their First Order Derivatives

Publication Year: 2013, Page(s):205 - 208
Cited by:  Papers (1)
| | PDF (1899 KB) | HTML

Recently, an optimal Prior-knowledge method for DOA estimation has been proposed. This method solely estimates a subset of DOA's accounting known ones. The global idea is to maximize the orthogonality between an estimated signal subspace and noise subspace by constraining the orthogonal noise-made projector to only project onto the desired unknown signal subspace. As it could be surprising, no def... View full abstract»

• ### Making a “Completely Blind” Image Quality Analyzer

Publication Year: 2013, Page(s):209 - 212
Cited by:  Papers (248)
| | PDF (563 KB) | HTML

An important aim of research on the blind image quality assessment (IQA) problem is to devise perceptual models that can predict the quality of distorted images with as little prior knowledge of the images or their distortions as possible. Current state-of-the-art “general purpose” no reference (NR) IQA algorithms require knowledge about anticipated distortions in the form of trainin... View full abstract»

• ### Improved Generalized Eigenvalue Proximal Support Vector Machine

Publication Year: 2013, Page(s):213 - 216
Cited by:  Papers (25)
| | PDF (825 KB) | HTML

In this letter, we propose an improved version of generalized eigenvalue proximal support vector machine (GEPSVM), called IGEPSVM for short. The main improvements are 1) the generalized eigenvalue decomposition is replaced by the standard eigenvalue decomposition, resulting in simpler optimization problems without the possible singularity. 2) An extra meaningful parameter is introduced, resulting ... View full abstract»

• ### Consistent Wiener Filtering for Audio Source Separation

Publication Year: 2013, Page(s):217 - 220
Cited by:  Papers (29)
| | PDF (874 KB) | HTML

Wiener filtering is one of the most ubiquitous tools in signal processing, in particular for signal denoising and source separation. In the context of audio, it is typically applied in the time-frequency domain by means of the short-time Fourier transform (STFT). Such processing does generally not take into account the relationship between STFT coefficients in different time-frequency bins due to ... View full abstract»

• ### Blind Signal Estimation in Widely-Linear Signal Models With Fourth-Order Circularity: Algorithms and Application to Receiver I/Q Calibration

Publication Year: 2013, Page(s):221 - 224
Cited by:  Papers (4)
| | PDF (1057 KB) | HTML

In-phase/quadrature (I/Q) imbalance degrades heavily the image rejection performance of direct-conversion radios. I/Q imbalance also changes the statistics of the received signal, and in particular makes a circular signal non-circular. This fact has been utilized in compensating receiver I/Q imbalances, utilizing second-order statistics. In this article, we investigate whether moment circularity o... View full abstract»

• ### On Optimal Linear Filtering of Speech for Near-End Listening Enhancement

Publication Year: 2013, Page(s):225 - 228
Cited by:  Papers (25)  |  Patents (1)
| | PDF (669 KB) | HTML

In this letter the focus is on linear filtering of speech before degradation due to additive background noise. The goal is to design the filter such that the speech intelligibility index (SII) is maximized when the speech is played back in a known noisy environment. Moreover, a power constraint is taken into account to prevent uncomfortable playback levels and deal with loudspeaker constraints. Pr... View full abstract»

• ### Analysis of the Characteristic of the Kalman Gain for 1-D Chaotic Maps in Cubature Kalman Filter

Publication Year: 2013, Page(s):229 - 232
Cited by:  Papers (3)
| | PDF (801 KB) | HTML

The characteristic of Kalman gain in a cubature Kalman filter for filtering 1-D chaotic signals is investigated. It is shown theoretically that the Kalman gain converges to zero for the case of periodic nonlinear systems, and it either approaches the Cramér-Rao lower bound or oscillates aperiodically for the case of chaotic nonlinear systems. Results from analysis of the Kalman gain are ve... View full abstract»

• ### JPEG Steganalysis With High-Dimensional Features and Bayesian Ensemble Classifier

Publication Year: 2013, Page(s):233 - 236
Cited by:  Papers (11)
| | PDF (795 KB) | HTML

This work proposes a JPEG steganalytic scheme based on high-dimensional features and Bayesian ensemble classifier. The proposed scheme employs 15700 dimension features calculated from the co-occurrence matrices of DCT coefficients and coefficient differences, which indicate the intra-block and inter-block dependencies of image content. Furthermore, a number of sub-classifiers trained on the featur... View full abstract»

• ### Full-Image Guided Filtering for Fast Stereo Matching

Publication Year: 2013, Page(s):237 - 240
Cited by:  Papers (8)  |  Patents (2)
| | PDF (597 KB) | HTML

A novel full-image guided filtering method is proposed. Different with many existing neighborhood filters, all input elements are employed during the proposed filtering approach. In addition, a novel scheme called weight propagation is proposed to compute support weights. It fulfills the requirements of edge preserving and low complexity. It is applied to the cost-volume filtering in the local ste... View full abstract»

• ### Supervised Low-Rank Matrix Recovery for Traffic Sign Recognition in Image Sequences

Publication Year: 2013, Page(s):241 - 244
Cited by:  Papers (7)
| | PDF (1033 KB) | HTML

Correlations in image sequences can be potentially useful for recovering feature representation and subsequently prompting classification performance, which are often neglected by traditional classification approaches. In this letter, we present a supervised low-rank matrix recovery model to leverage these correlations for classification tasks by introducing a supervised penalty term to the classi... View full abstract»

• ### Bivariate Empirical Mode Decomposition for Unbalanced Real-World Signals

Publication Year: 2013, Page(s):245 - 248
Cited by:  Papers (16)
| | PDF (758 KB) | HTML

The bivariate empirical mode decomposition (BEMD) algorithm employs uniform sampling on a circle to perform projections in multiple directions, in order to calculate the local mean of a bivariate signal. However, this approach is adequate only for equal powers in both the data channels within a bivariate signal, and results in suboptimal performance for data channels exhibiting power imbalance, a ... View full abstract»

• ### Bayesian Denoising: From MAP to MMSE Using Consistent Cycle Spinning

Publication Year: 2013, Page(s):249 - 252
Cited by:  Papers (9)
| | PDF (719 KB) | HTML

We introduce a new approach for the implementation of minimum mean-square error (MMSE) denoising for signals with decoupled derivatives. Our method casts the problem as a penalized least-squares regression in the redundant wavelet domain. It exploits the link between the discrete gradient and Haar-wavelet shrinkage with cycle spinning. The redundancy of the representation implies that some wavelet... View full abstract»

• ### Spectral Domain Speech Enhancement Using HMM State-Dependent Super-Gaussian Priors

Publication Year: 2013, Page(s):253 - 256
Cited by:  Papers (12)
| | PDF (985 KB) | HTML

The derivation of MMSE estimators for the DFT coefficients of speech signals, given an observed noisy signal and super-Gaussian prior distributions, has received a lot of interest recently. In this letter, we look at the distribution of the periodogram coefficients of different phonemes, and show that they have a gamma distribution with shape parameters less than one. This verifies that the DFT co... View full abstract»

• ### One-Bit Quantizer Design for Multisensor GLRT Fusion

Publication Year: 2013, Page(s):257 - 260
Cited by:  Papers (12)
| | PDF (732 KB) | HTML

In this letter, we consider a decentralized detection problem in which a number of sensor nodes collaborate to detect the presence of an unknown deterministic signal. Due to stringent power/bandwidth constraints, each sensor quantizes its local observation into one bit of information. The binary data are then sent to the fusion center (FC), where a generalized likelihood ratio test (GLRT) detector... View full abstract»

• ### Variational Bayesian View of Weighted Trace Norm Regularization for Matrix Factorization

Publication Year: 2013, Page(s):261 - 264
Cited by:  Papers (1)
| | PDF (1064 KB) | HTML

Matrix factorization with trace norm regularization is a popular approach to matrix completion and collaborative filtering. When entries of the matrix are sampled non-uniformly (which is the case for collaborative prediction), a properly weighted correction to the trace norm regularization is known to improve the performance dramatically. While the weighted trace norm regularization has been rigor... View full abstract»

• ### Compressed Sensing via Dual Frame Based $ell_{1}$-Analysis With Weibull Matrices

Publication Year: 2013, Page(s):265 - 268
Cited by:  Papers (2)
| | PDF (1200 KB) | HTML

This letter considers the problem of recovering signals via dual frame based ℓ1-analysis model under the assumption that signals are compressible in a general frame. Our main result shows that Weibull random matrices (not only subgaussian matrices) with optimal number of measurements could guarantee accurate recovery of signals with high probability. We derive that result by gene... View full abstract»

• ### An Information-Geometric Characterization of Chernoff Information

Publication Year: 2013, Page(s):269 - 272
Cited by:  Papers (6)
| | PDF (1297 KB) | HTML

The Chernoff information was originally introduced for bounding the probability of error of the Bayesian decision rule in binary hypothesis testing. Nowadays, it is often used as a notion of symmetric distance in statistical signal processing or as a way to define a middle distribution in information fusion. Computing the Chernoff information requires to solve an optimization problem that is numer... View full abstract»

• ### Cooperative Estimation of Path Loss in Interference Channels Without Primary-User CSI Feedback

Publication Year: 2013, Page(s):273 - 276
| | PDF (1095 KB) | HTML

Knowledge of the channel path-loss between a primary user and a secondary user in underlay cognitive radio systems could be vital for deciding how a secondary user accesses a specific frequency band. The conventional way to acquire this knowledge relies on some collaboration with primary user systems. This letter proposes a novel cooperative technique for estimating the path-loss parameter in cogn... View full abstract»

• ### Selection Combining for Differential Amplify-and-Forward Relaying Over Rayleigh-Fading Channels

Publication Year: 2013, Page(s):277 - 280
Cited by:  Papers (6)
| | PDF (1013 KB) | HTML

This letter proposes and analyses selection combining (SC) at the destination for differential amplify-and-forward (D-AF) relaying over slow Rayleigh-fading channels. The selection combiner chooses the link with the maximum magnitude of the decision variable to be used for non-coherent detection of the transmitted symbols. Therefore, in contrast to the maximum ratio combining (MRC), no channel inf... View full abstract»

## Aims & Scope

The IEEE Signal Processing Letters is a monthly, archival publication designed to provide rapid dissemination of original, cutting-edge ideas and timely, significant contributions in signal, image, speech, language and audio processing.

Full Aims & Scope

## Meet Our Editors

Editor-in-Chief
James E. Fowler
Dept Electrical & Computer Engineering
Associate Director
Distributed Analytics and Security Institute
Mississippi State University
Mississippi State, MS 39762 USA
fowler@ece.msstate.edu