Linguistic Processing for Speech Synthesis

Abstract

An important part of any text-to-speech (TTS) text-to-speech synthesis system is the linguistic processing linguistic processing component that takes input text and converts it into a feature representation from which actual synthesis can proceed. Linguistic analysis is hard, in a large measure because written language massively underspecifies linguistic information. This chapter reviews several issues in linguistic analysis starting from low-level text normalization issues, and ending with higher-level problems such as accent prediction and document-level analysis. We end with some prognosis of the future prospects for improvements over current technology.