Any text-to-speech system has a subsystem (duration system) that computes speech timing. How does one construct a duration system that accurately mimics natural speech? This paper discusses a particular type of data analysis method for the statistical analysis of natural speech durations, ordinal data analysis, and shows how it can be used for the construction of duration systems.
Cite as: Santen, J.P.H.v. (1990) Deriving text-to-speech durations from natural speech. Proc. First ESCA Workshop on Speech Synthesis (SSW 1), 157-160
@inproceedings{santen90_ssw,
author={Jan P. H. van Santen},
title={{Deriving text-to-speech durations from natural speech}},
year=1990,
booktitle={Proc. First ESCA Workshop on Speech Synthesis (SSW 1)},
pages={157--160}
}