Can Computers Read a Text with Stress?

Abstract

Today prosodic elements such as stress, intonation and melody can be examined through computer-assisted techniques. The identification and analysis of acoustic qualities provide significant clues as to the suprasegmental aspects of speech. In this study a system was designed to enable speech synthesis using a Turkish text. This synthesizer was used to analyze the melodic sructures of selected sentences. Any speech synthesized by a computer needs to be equipped with a melodic model so that it will sound natural to the ear. Within the context of this study a melodic model was also suggested, and the elements of this model were analyzed and discussed in terms of the rules of linguistics.