This paper describes our system for SemEval-2010 Task 8 on multi-way classification of semantic relations between nominals. First, the type of semantic relation is classified. Then a relation typespecific classifier determines the relation direction. Classification is performed using SVM classifiers and a number of features that capture the context, semantic role affiliation, and possible pre-e...

In this paper, a ray-tracing technique to predict the propagation channel parameters in indoor scenarios is presented. It is a deterministic technique, fully three-dimensional, based on geometrical optics (GO) and the uniform theory of diffraction (UTD). A model of plane facets is used for the geometrical description of the environment. The ray tracing is accelerated considerably by using the A...

This document briefly describes the systems submitted by the Center for Robust Speech Systems (CRSS) from The University of Texas at Dallas (UTD) for the 2012 NIST Speaker Recognition Evaluation. We developed a state-of-the-art i-vector based speaker recognition system [1]. Probabilistic linear discriminant analysis (PLDA) [2] along with several other backends are used for channel/noise compens...

The accurate modelling of fundamental frequency, or F0, in HMM-based speech synthesis is a critical factor in achieving high quality speech. However, it is also difficult because F0 values are normally considered to depend on a binary voicing decision such that they are continuous in voiced regions and undefined in unvoiced regions. A widely used solution is to use a multi-space probability dis...

This paper presents GTD-POP, a planning methodology based on the Generate, Test and Debug paradigm. GTD-POP’s goal is to achieve a compromise between planning efficiency and soundness by using associational knowledge to guide its search for interaction checks in a partially-ordered plan. This paper describes the GTD-POP and discusses issues involved in evaluating the behavior of practical plann...

A new efficient technique for the analysis of complex antenna around a scatterer is proposed in this paper, termed the iterative vector fields with uniform geometrical theory of diffraction (UTD) technique. The complex field vector components on the closed surface enclosing the antenna without platform are computed by higher order Method of Moments (MOM), and the scattered fields from the platf...

This study describes systems submitted by the Center for Robust Speech Systems (CRSS) from the University of Texas at Dallas (UTD) to the 2016 National Institute of Standards and Technology (NIST) Speaker Recognition Evaluation (SRE). We developed 4 UBM and DNN i-vector based speaker recognition systems with alternate data sets and feature representations. Given that the emphasis of the NIST SR...

Appropriate formulation of the UTD diffracted field is important for propagation prediction. Among the wedge. diffraction solutions for nonperfectly conducting surfaces in the literature, exact formulations are mostly based on Maliuzhinets's derivation [1] and are computationally prohibitive for practical applications. On the other hand, heuristic formulations, modified from the UTD diffraction...

We give an introduction into diffraction theory for aperiodic order. We focus on an approach via dynamical systems and the phenomenon of pure point diffraction. We review recent results and sketch proofs. We then present a new uniform Wiener/Wintner type result generalizing various earlier results of this type.

Off-policy learning refers to the problem of learning the value function of a way of behaving, or policy, while following a different policy. Gradient-based off-policy learning algorithms, such as GTD and TDC/GQ [13], converge even when using function approximation and incremental updates. However, they have been developed for the case of a fixed behavior policy. In control problems, one would ...