Search results

Section: Publications & Resources

Publication: IEEE Transactions on Signal Processing

A new technique for locating a moving source radiating a wide-band almost-cyclostationary signal is proposed. For this purpose, the signals received on two possibly moving sensors are modeled as jointly spectrally correlated, a new nonstationarity model that allows one to describe the Doppler effect accounting for a time-scale or time-stretch factor in the complex envelopes of the received signals.

Section: Publications & Resources

Publication: IEEE Transactions on Signal Processing

We study model recovery for data classification, where the training labels are generated from a one-hidden-layer neural network with sigmoid activations, also known as a single-layer feedforward network, and the goal is to recover the weights of the neural network. We consider two network models, the fully-connected network (FCN) and the non-overlapping convolutional neural network (CNN).

Section: Publications & Resources

Publication: IEEE Transactions on Signal Processing

Speech dereverberation has been an important component of effective far-field voice interfaces in many applications. Algorithms based on multichannel linear prediction (MCLP) have been shown to be especially effective for blind speech dereverberation and numerous variants have been introduced in the literature. Most of these approaches can be derived from a common framework, where the MCLP problem for speech dereverberation is formulated as a weighted least squares problem that can be solved analytically.

Section: Publications & Resources

Publication: IEEE Open Journal of Signal Processing

Principal component analysis is one of the most commonly used methods for dimensionality reduction in signal processing. However, the most commonly used PCA formulation is based on the L2 -norm, which can be highly influenced by outlier data. In recent years, there has been growing interest in the development of more robust PCA methods. 

Section: Publications & Resources

The DSLW team is inviting you to submit regular papers to the 2021 IEEE Data Science & Learning Workshop (DSLW 2021), a new workshop organized by the IEEE Signal Processing Society. The workshop aims to bring together researchers in academia and industry to share the most recent and exciting advances in data science, learning theory and applications.

Section: Publications & Resources

The DSLW team is inviting you to submit regular papers to the 2021 IEEE Data Science & Learning Workshop (DSLW 2021), a new workshop organized by the IEEE Signal Processing Society. The workshop aims to bring together researchers in academia and industry to share the most recent and exciting advances in data science, learning theory and applications.

Section: Events

Publication: IEEE Transactions on Multimedia

Manuscript Due: February 28, 2021 Publication Date: Early 2022 CFP Document

Section: Publications & Resources

Dr. Hema A. Murthy received the bachelor's degree from Osmania University, Hyderabad, India, in 1980, the master's degree from McMaster University, Hamilton, Canada, in 1986, and the Ph.D. degree from the Indian Institute of Technology (IIT) Madras, Chennai, India, in 1992.

Section: Publications & Resources

Publication: IEEE Transactions on Image Processing

We present a method to compress geometry information of point clouds that explores redundancies across consecutive frames of a sequence. It uses octrees and works by progressively increasing the resolution of the octree. At each branch of the tree, we generate an approximation of the child nodes by a number of methods which are used as contexts to drive an arithmetic coder.

Section: Publications & Resources

Publication: IEEE Transactions on Multimedia

The scalable high efficiency video coding (SHVC) is an extension of high efficiency video coding (HEVC). It introduces multiple layers and inter-layer prediction, thus significantly increases the coding complexity on top of the already complicated HEVC encoder. In inter prediction for quality SHVC, in order to determine the best possible mode at each depth level, a coding tree unit can be recursively split into four depth levels.