Overview of Current Text-to-Speech Techniques: Part I - Text and Linguistic Analysis
MD EDGINGTON, A. Lowry, Philip J. B. Jackson, Andrew Breen, Stephen Minnis · UEA Digital Repository (University of East Anglia) · 1996
Speech synthesis is an increasingly important technique in interactive voice systems, as shown elsewhere in this issue, and is crucial to the next generation of spoken language dialogue systems. Described here are many of the techniques and algorithms used in state-of-the art commercial text-to-speech synthesisers, where real world issues of robustness, reliability and processing cost compete with the specific requirements of naturalness and intelligibility. This paper describes techniques used in text and linguistic analysis, which build up a linguistic structure defining the important features of the input text. This linguistic structure is then used by the prosody and speech generation processes to create the synthetic speech signal.