In this paper we report on some recent improvements on the acoustic modeling in a segment-based speech recognition system. Context-dependent segment models and improved pronunciation modeling are shown to reduce word error rates in a telephone-based, conversational system by over 18%, while the technique of Gaussian selection reduces overall computation by more than a factor of two.

This paper addresses the theoretical modeling of the dynamics of a pressure-operated soft snake robot. An accurate dynamic model is a fundamental requirement for optimization, control, navigation, and learning algorithms for a mobile robot that can undergo serpentine locomotion. Such algorithms can be readily implemented for traditional rigid robots, but remain a challenge for nonlinear and low...

Random copolymers of epsilon-caprolactone and 2-oxo-12-crown-4 ether, poly(CL-co-OC), were used as soft segments in the synthesis of a set of poly(urethane)urea thermoplastic elastomers. With increasing OC content, the soft segment crystallinity decreased, which influenced the mechanical properties: strain induced crystallization disappeared upon the introduction of OC into poly(CL). The materi...

A method that performs multiresolution enhancement, adaptive to breast components, for optimal visualization of the entire breast area is presented. The method includes an edge detection step to distinguish breast area from mammogram background and employs Gaussian mixture modeling to segment breast components (uncompressed fat, fat and dense). The original image is decomposed using a redundant...

The complexities of modeling uncertain data in economics, engineering, environmental science, sociology, medical science and many other fields can not be successfully dealt with by classical methods. While probability theory, fuzzy set theory,rough set theory, vague set theory and the interval mathematics are useful approaches to describing uncertainty, each of these theories has its inherent d...

Car-following models, as the most popular microscopic traffic flow modeling, is increasingly being used by transportation experts to evaluate new Intelligent Transportation System (ITS) applications. A number of factors including individual differences of age, gender, and risk-taking behavior, have been found to influence car-following behavior. This paper presents a novel idea to calculate ...

car-following models, as the most popular microscopic traffic flow modeling, is increasingly being used by transportation experts to evaluate new intelligent transportation system (its) applications. a number of factors including individual differences of age, gender, and risk-taking behavior, have been found to influence car-following behavior. this paper presents a novel idea to calculate the...

nowadays, groundwater resources play a vital role as a source of drinking water in arid and semiarid regions and forecasting of pollutants content in these resources is very important. therefore, this study aimed to compare two soft computing methods for modeling cd, pb and zn concentration in groundwater resources of asadabad plain, western iran. the relative accuracy of several soft computing...