Abstract
In this work, a speech recognition system including a simple word-by-word translation system for mobile devices such as mobile phones and PDAs is planned and ultimately implemented on a target device. In the rst part the theoretical basis of speech production and speech recognition are examined. Subsequently prominent techniques used in speech recognition are presented. Furthermore the potential sources of interferences and restrictions in mobile applications are examined. In the second part the Java ME platform is presented, which serves as the basis for the implementation of the speech recognition system in practice. The development process is explained including the technology selection and the implementation. Optimization steps, problems and solutions in the practical work are illustrated. Finally, the experimental validation provides information and insights on the implemented system.
Reference
Morgenbesser, W. (2010). Spracherkennung in mobilen Endgeräten [Diploma Thesis, Technische Universität Wien]. reposiTUm. http://hdl.handle.net/20.500.12708/160867