Assigning Intonation Elements And Prosodic Phrasing For English Speech Synthesis From High Level Linguistic Input

This paper describes a method for generating intonation events and prosodic phrasing from a high level linguistic description. Specifically, the input consists of information normally available from linguistic processing: part of speech, constituent structure and, importantly, speech act. The generated output contains explicit intonational events from which an F 0 contour may be generated. Prosody can be controlled via features in the input describing the function of words and phrases without direct reference to intonation. The results are evaluated against natural spoken sentences. 1. INTRODUCTION When a speech synthesizer is used as an integral part of a speech translation system, the input to the synthesis sub-system need not be simple unlabelled text. Structured information including speech act type, part of speech, and syntactic constituent structure already exists in earlier components of the translation system. This information can be used directly enabling the synthesis syste..