Speech synthesis in the mobile user interface

This paper describes the development of a mobile application platform featuring an integrated text-to-speech synthesis engine as one of the core components. The work reported herein formed part of an international consortium project entitled Mobile E-learning for Africa (MELFA), which aimed to develop an application featuring reading and literacy training components, in English and one African language, isiXhosa. Particular attention is paid to the design and development of the mobile application platform, the embedding of the speech generation component and the multimodal user interface. The primary aims of the proposed platform are to support the widest range of applications that could benefit from speech output and for the applications to reach the widest possible audience.