Report (M.S.)--Virginia Polytechnic Institute and State University, 1994. / Abstract. Includes bibliographical references (leaves 55-56). Also available via the Internet.

Thesis (M.S.)--Rochester Institute of Technology, 1995. / Typescript. Includes bibliographical references (leaves 186-187).

Masters of Science / Recognising and estimating gestures is a fundamental aspect towards translating from a sign language to a spoken language. It is a challenging problem and at the same time, a growing phenomenon in Computer Vision. This thesis presents two approaches, an example-based and a learning-based approach, for performing integrated detection, segmentation and 3D estimation of the human upper body from a single camera view. It investigates whether an upper body pose can be estimated from a database of exemplars with labelled poses. It also investigates whether an upper body pose can be estimated using skin feature extraction, Support Vector Machines (SVM) and a 3D human body model. The example-based and learning-based approaches obtained success rates of 64% and 88%, respectively. An analysis of the two approaches have shown that, although the learning-based system generally performs better than the example-based system, both approaches are suitable to recognise and estimate upper body poses in a South African sign language recognition and translation system. / South Africa

In this thesis we investigate the potential of developing a speech recognition system based on a recently introduced artificial neural network (ANN) technique, namely Reservoir Computing (RC). This technique has, in theory, a higher capability for modelling dynamic behaviour compared to feed-forward ANNs due to the recurrent connections between the nodes in the reservoir layer, which serves as a memory. We conduct this study on the Arabic language, (one of the most spoken languages in the world and the official language in 26 countries), because there is a serious gap in the literature on speech recognition systems for Arabic, making the potential impact high. The investigation covers a variety of tasks, including the implementation of the first reservoir-based Arabic speech recognition system. In addition, a thorough evaluation of the developed system is conducted including several comparisons to other state- of-the-art models found in the literature, and baseline models. The impact of feature extraction methods are studied in this work, and a new biologically inspired feature extraction technique, namely the Auditory Nerve feature, is applied to the speech recognition domain. Comparing different feature extraction methods requires access to the original recorded sound, which is not possible in the only publicly accessible Arabic corpus. We have developed the largest public Arabic corpus for isolated words, which contains roughly 10,000 samples. Our investigation has led us to develop two novel approaches based on reservoir computing, ESNSVMs (Echo State Networks with Support Vector Machines) and ESNEKMs (Echo State Networks with Extreme Kernel Machines). These aim to improve the performance of the conventional RC approach by proposing different readout architectures. These two approaches have been compared to the conventional RC approach and other state-of-the- art systems. Finally, these developed approaches have been evaluated on the presence of different types and levels of noise to examine their resilience to noise, which is crucial for real world applications.

Bibliography: leaves [238]-244 / xi, 244 leaves : ill ; 30 cm. / Title page, contents and abstract only. The complete thesis in print form is available from the University Library. / Thesis (Ph.D.)--University of Adelaide, Dept. of Computer Science, 1985

We present a multifaceted investigation into the relevance of word order in machine translation. We introduce two tools, DTED and DERP, each using dependency structure to detect differences between the structures of machine-produced translations and human-produced references. DTED applies the principle of Tree Edit Distance to calculate edit operations required to convert one structure into another. Four variants of DTED have been produced, differing in the importance they place on words which match between the two sentences. DERP represents a more detailed procedure, making use of the dependency relations between words when evaluating the disparities between paths connecting matching nodes. In order to empirically evaluate DTED and DERP, and as a standalone contribution, we have produced WOJ-DB, a database of human judgments. Containing scores relating to translation adequacy and more specifically to word order quality, this is intended to support investigations into a wide range of translation phenomena. We report an internal evaluation of the information in WOJ-DB, then use it to evaluate variants of DTED and DERP, both to determine their relative merit and their strength relative to third-party baselines. We present our conclusions about the importance of structure to the tools and their relevance to word order specifically, then propose further related avenues of research suggested or enabled by our work.