Text-to-speech processing using African language as case study

This paper presents Text-to-Speech processing using text mark-up language, such as eXtendible Markup Language, Text-to-speech synthesis, and Web technologies, which provide a more powerful platform for accessing it. In this paper, the specification and design of computational mechanisms for realizing the various components of the Text-to-speech synthesis system using one of African most popular Language “Yorùbá” as a case study is discussed. The design of the High Level and Low Level synthesis modules of the Text-to-speech synthesis system are discussed. An implementation based on Finite State Transducer Technology and Fuzzy logic technique is also presented. Using experiments, we are able to obtain 85% intelligibility and 70% naturalness accuracy for the Text-to-speech synthesis system.