Petra Witschel

Analysis of a Complex System for Electrical Mobility Using a Model-Based Engineering Approach Focusing on Simulation

Abstract Electrical mobility is a highly innovative field with fast development cycles and rapid evolution of its core architectures. Also, the system complexity is quickly increasing. Especially challenging in industrial settings is the tight integration of mechanical, electrical and software domains within so called mechatronic systems. In modern engineering processes, simulation models are used for the analysis of different aspects of such systems. In this paper, we report our experience with a model-based and simulation-focused methodology for system engineering which allows quick validation of different architectural decisions at early development phases. We present an approach for integration between engineering tools using the automated generation of simulation models from the system description. The feasibility of the proposed methods is demonstrated with a sample application from electrical mobility, which also exemplifies the challenges of the integrated analysis of mechatronic systems. Specialized modeling languages based on the UML standard are used for the overall description of the system, for the analysis of its functionality, and for the specification of combined configurations. Another standard, Modelica language, is used for the simulation of different physical aspects of the system.

A PC-based real-time large vocabulary continuous speech recognizer for German

A large vocabulary speech recognizer for German is presented. The main properties of the recognizer are speaker independence, continuous speech input and real-time operation. It is integrated into a client/server framework, which allows for simple porting between different hard- and software platforms. Methods like simplified language model spreading in beam search and specialized word-begin and -end modelling are introduced in order to achieve real-time operation on a Pentium-based PC. Recognition tests for two different dictation applications (controlled speech newspaper dictation and spontaneous speech medical dictation) are presented showing the importance of adding efforts in the modelling of spontaneous speech.

Experiments in Dialogue Context Dependent Language Modelling

The German prototype (SUn Germ) of the European project SUndial 1 aims at a telephone based real time system for oral dialogues to inquire a database on intercity train schedules. To enhance system Performance one of our goals is to improve the recognition accuracy by minimizing the perplexity. We will show that our bigram language model component which can be dynamically changed according to the context of the dialogue, can further reduce this perplexity. This paper describes the integration of linguistic knowledge into the continuous speech recognizer2. Especially our experiments in the interaction of the language model component and the dialogue manager are presented. In our evaluation part we compare our approaches with and without dynamically varied language models by an overview of results of the Performance measurement.