Learn More
Due to the limitation of single-level classification, existing fusion techniques experience difficulty in improving the performance of language identification when the number of languages and features are further increased. Given that the similarity of feature distribution between different languages may vary, we propose a novel hierarchical language(More)
The aim of this study was to test the sensitivity and specificity of diffusion-weighted MRI for the detection of acute spinal cord injury. Forty female New Zealand white rabbits were randomly divided into four groups: the mild, moderate and severe injury groups, and the control (sham operation) group. Contusion of the spinal cord was induced using a(More)
Neuroinflammation plays an important role in cerebral ischemia/reperfusion (I/R) injury. The P2X7 receptor (P2X7R) has been reported to be involved in the inflammatory response of many central nervous system diseases. However, the role of P2X7Rs in transient global cerebral I/R injury remains unclear. The purpose of this study is to determine the effects of(More)
This study reports on cervical magnetic resonance imaging (MRI) performed in the fully flexed position in 13 male patients with Hirayama disease and 12 normal controls (males). The anterior-posterior diameter of the cervical cord at the superior margin of the C6 vertebral body was measured, as well as the angle between adjacent cervical bodies. Localized(More)
Cognitive load variations have been found to impact multimodal behaviour, in particular, features of spoken input. In this paper, we present a design and implementation of a user study aimed at soliciting natural speech at three different levels of cognitive load. Some of the speech data produced was then used to train a number of models to automatically(More)
Despite recent advances in the understanding of the biology of renal cell carcinoma (RCC), successful surgical treatment and implementation of novel‑targeted therapies, the prognosis for RCC patients remains poor. Late presentation, tumor heterogeneity and in particular the lack of molecular biomarkers for early detection, classification and the(More)
A novel approach of combining cepstral features and prosodic features in language identification is presented in this paper. This combination approach shows a significant improvement on a GMM-UBM based language identification (LID) system which utilizes modern shifted delta cepstrum (SDC) and feature warping techniques. The proposed system achieves a high(More)