Text-to-Speech Synthesis

Abstract

This paper presents an overview of the problems that occur during text-to-speech (TTS) conversion and describes the particular solutions to these problems taken within the AT&T Bell Laboratories TTS system. In addition to discussing the linguistic and speech analysis issues that must be addressed in a high-quality TTS system, this paper also outlines the modular architecture of the AT&T Bell Laboratories TTS system and the advantages of its modular design.