The performance of the existing speech recognition systems degrades rapidly in the presence of background noise. A novel representation of the speech signal, which is based on Linear Prediction of the One-Sided Autocorrelation sequence (OSALPC), has shown to be attractive for noisy speech recognition because of both its high recognition performance with respect to the conventional LPC in severe...

English. Neural machine translation (NMT) recently redefined the state of the art in machine translation, by introducing deep learning architecture that can be trained end-to-end. One limitation of NMT is the difficulty to learn representations of rare words. The most common solution is to segment words into subwords, in order to allow for shared representations of infrequent words. In this pap...

Keywords Release of indeterminate sentence prisoner, Parole Board reconsideration, functus officio, judicial review

There are few research studies documenting the effectiveness of Computer-Based Speech Training (CBST) systems. This paper evaluates the effectiveness of the IBM SpeechViewer CBST combined with a newly developed rate control program (The Stepping Stones Game) for improving speech production in individuals with dysarthria. Three subjects were studied using a single-subject multiple baseline desig...

AT ONE POINT in our history, nobody would have imagined releasing a prison inmate into society with little supervision or support. As Simon (1993) shows, well into the 1950s, such a practice would have been unthinkable. From the implementation of parole as a widespread correctional policy, a key component of release from prison was securing employment. It was assumed that offenders would be "di...