but effective GMMs for likelihood functions, a universal background model (UBM) for alternative speaker representation, and a form of Bayesian adaptation to derive speaker models from the UBM. The development and use of a handset detector and score normalization to greatly improve verification performance

Several parametric representations of the acoustic signal were compared as to word recognition performance in a syllable-oriented continuous speech recognition system. The vocabulary in-cluded many phonetically similar monosyllabic words, therefore the emphasis was on ability to retain

variety of temporal logic: alternating-time temporal logic offers selective quantification over those paths that are possible outcomes of games, such as the game in which the system and the environment alternate moves. While linear-time and branching-time logics are natural specification languages

We present an unsupervised technique for visual learning which is based on density estimation in high-dimensional spaces using an eigenspace decomposition. Two types of density estimates are derived for modeling the training data: a multivariate Gaussian (for unimodal distributions) and a Mixture-of-Gaussians model (for multimodal distributions). These probability densities are then used to formulate a maximum-likelihood estimation framework for visual search and target detection for automatic object recognition and coding. Our learning technique is applied to the probabilistic visual modeling, detection, recognition, and coding of human faces and non-rigid objects such as hands.

categorization in terms of learning speed, realtime classification speed, and classification accuracy. We also examine training set size, and alternative document representations. Very accurate text classifiers can be learned automatically from training examples. Linear Support Vector Machines (SVMs

This paper examines the structure of option valuation problems and develops a new technique for their solution. It also introduces several jump and diffusion processes which have nol been used in previous models. The technique is applied lo these processes to find explicit option valuation formulas, and solutions to some previously unsolved problems involving the pricing ofsecurities with payouts and potential bankruptcy. 1.

How do people know as much as they do with as little information as they get? The problem takes many forms; learning vocabulary from text is an especially dramatic and convenient case for research. A new general theory of acquired similarity and knowledge representation, latent semantic analysis

will incorporate a theoretically justi ed representation of the native speaker's linguistic knowledge (a grammar) as a component separate both from the computational mechanisms that operate on it (a processor) and from other nongrammatical processing parameters that might influence the processor

KL-ONE lets one define and use a class of descriptive terms called Concepts, where each Concept denotes a set of objects A subsumption relation between Concepts is defined which is related to set inclusion by way of a semantics for Concepts. This subsumption relation defines a partial order on Concepts, and KL-ONE organizes all Concepts into a taxonomy that reflects this partial order. Classification is a process that takes a new Concept and determines other Concepts that either subsume it or that it subsumes, thereby determining the location for the new Concept within a given taxonomy. We discuss these issues and demonstrate some uses of the classification algorithm.

Abstract not found