The Nuisance Attribute Projection (NAP) with labeled data provides an effective approach for improving the speaker recognition performance in the state-of-art speaker recognition system by removing unwanted speaker channel and handsets variation. However, the requirement for the labeled NAP training data may limit its practical application. In this paper, we propose an unsupervised clustering s...

In this paper, we propose the use of cluster adaptive training (CAT) weights as features in support vector machine (SVM) based text-independent verification task. The speaker utterance is characterized by a vector of cluster weights, which are extracted during the cluster adaptive training process. The effects of the number of classes, which are obtained by partitioning the components of the mo...

We show how to efficiently compute 2D polyhedral bounds of the (elliptic) perspective projection of a 3D sphere that has been clipped to the near plane. For the special case of a 2D axis-aligned bounding box, the algorithm is especially efficient. This has applications for bounding the screen-space effect of an emitter under deferred shading, bounding the kernel in density estimation during ima...

A significant obstacle to developing high performance Deep Learning algorithms for Automated Threat Detection (ATD) in security X-ray imagery, is the difficulty of obtaining large training datasets. In our previous work, we circumvented this problem for ATD in cargo containers, using Threat Image Projection and data augmentation. In this work, we investigate whether data scarcity for other moda...

We demonstrate the application of Nuisance Attribute Projection (NAP), Within-Class Covariance Normalization (WCCN), a new standard kernel, and keyword weighting for the keywordbased HMM supervector speaker recognition system. On our development set (SRE04 8-side training), we achieve 22.6% and 16.2% EER improvements using NAP and WCCN respectively, a 19.5% EER improvement using NAP and WCCN jo...

In several applications of data mining to high-dimensional data, clustering techniques developed for low-to-moderate sized problems obtain unsatisfactory results. This is an aspect of the curse of dimensionality issue. A traditional approach is based on representing the data in a suitable similarity space instead of the original high-dimensional attribute space. In this paper, we propose a solu...

Person re-identification has recently attracted a lot of attention in the computer vision community. This is in part due to the challenging nature of matching people across cameras with different viewpoints and lighting conditions, as well as across human pose variations. The literature has since devised several approaches to tackle these challenges, but the vast majority of the work has been c...

In recent years methods for modeling and mitigating variational nuisances have been introduced and refined. A primary emphasis in this years NIST 2008 Speaker Recognition Evaluation (SRE) was to greatly expand the use of auxiliary microphones. This offered the additional channel variations which has been a historical challenge to speaker verification systems. In this paper we present the MIT Li...

Compensation of cepstral features for mismatch due to dissimilar train and test conditions has been critical for good performance in many speech applications. Mismatch is typically due to variability from changes in speaker, channel, gender, and environment. Common methods for compensation include RASTA, mean and variance normalization, VTLN, and feature warping. Recently, a new class of subspa...

For many decision problems with uncertainty, triangular intuitionistic fuzzy number is a useful tool in expressing ill-known quantities. This paper develops a novel decision method based on zero-sum game for multiple attribute decision making problems where the attribute values take the form of triangular intuitionistic fuzzy numbers and the attribute weights are unknown. First, a new value ind...