Matching a tone-based and tune-based approach to English intonation for concept-to-speech generation

Abstract

The paper describes the results of a comparison of two annotation systems for intonation, the tone-based TOBI approach and the tune-based approach proposed by Systemic Functional Grammar (SFG). The goal of this comparison is to define a mapping between the two systems for the purpose of concept-to-speech generation of English. Since TOBI is widely used in speech synthesis and SFG is widely used in natural language generation and offers a linguistically motivated account of intonation, it appears a promising step to combine the two approaches for concept-to-speech. A corpus of English utterances has been analysed with both TOBI and SFG categories; comparison of the analysis results has lead to the identification of some basic equivalents between the two systems on which a mapping can be based.