Applications of support vector machines to speech recognition

Recent work in machine learning has focused on models, such as the support vector machine (SVM), that automatically control generalization and parameterization as part of the overall optimization process. In this paper, we show that SVMs provide a significant improvement in performance on a static pattern classification task based on the Deterding vowel data. We also describe an application of SVMs to large vocabulary speech recognition and demonstrate an improvement in error rate on a continuous alphadigit task (OGI Alphadigits) and a large vocabulary conversational speech task (Switchboard). Issues related to the development and optimization of an SVM/HMM hybrid system are discussed.     

Effects of processing parameters on axial stiffness of self‐reinforced polyethylene composites

Self‐reinforced polyethylene composites have proven to be promising candidate materials for a number of wear‐resistance and bioimplant applications. In this study, we investigated the effects of processing parameters on the elastic modulus of self‐reinforced high‐density polyethylene (HDPE) composites. The processing parameters investigated were the cooling rate, processing pressure, temperature, and duration. Our results showed an optimum processing temperature, pressure, and duration that were matrix‐dependent. In addition, for an HDPE matrix, the slower the composite cooling rate was, the higher the composite modulus was. © 2001 John Wiley & Sons, Inc. J Appl Polym Sci 81: 1136–1141, 2001