Automatic spoken language assessment systems are becoming increasingly important to meet the demand for English second language learning. This is a challenging task due to the high error rates of, even state-of-the-art, non-native speech recognition. Consequently current systems primarily assess fluency and pronunciation. However, content assessment is essential for full automation. As a first ...

The purpose of authorship search is to identify documents written by a particular author in large document collections. Standard search engines match documents to queries based on topic, and are not applicable to authorship search. In this paper we propose an approach to authorship search based on information theory. We propose relative entropy of style markers for ranking, inspired by the lang...

This paper presents a step towards the design of a novel test for simultaneous identification of all the stiffness components of orthotropic composite materials. A simulator was adopted to numerically simulate the whole identification process. Synthetic images were generated and then processed by Digital Image Correlation (DIC) to calculate the strain fields. The Virtual Fields Method (VFM) was...

abstract: Shear design models in reinforced concrete structures depend on stress transfer through cracks. Such mechanism is influenced by the displacement and roughness of opposite faces generated during cracking. reduced when an aggregate particle fractured leading to a smoother crack as found lightweight high strength concrete. This study evaluated ultimate shear sand-lightweight conventional...

In this paper we investigate the performance of different classification paradigms, testing each with a range of acoustic features, to find a system that is well suited to speaker likeability classification. We introduce a Sparse Representation Classifier for paralinguistic classification and explore the role of training data selection for a GMM classifier. Results demonstrate that (1) Single d...