This paper describes research behind a Large-Vocabulary Continuous Speech Recognition (LVCSR) system for the transcription of Senate speeches for the Polish language. The system utilizes severalcomponents: a phonetic transcription system, language and acoustic model training systems, a Voice Activity Detector (VAD), a LVCSR decoder, and a subtitle generator and presentation system. Some of the modules relied on already available tools and some had to be made from the beginning but the authors ensured that they used the most advanced techniques they had available at the time. Finally, several experiments were performed to compare the performance of both more modern and more conventional technologies.
The paper puts forward and implements a method of designing and creating a modelling simulation environment for extensive and complete analysis of economical lighting on highways. From a general design viewpoint, the proposed solution explores the concept of a network description language (SMOL), which has been designed to describe the necessary network functions, mechanisms, and devices for the purpose of their computer simulation and verification. The presented results of the performed research confirm the usability of intelligent lighting on highways, both in the sense of the design concept and in the aspect of saving energy.