This paper presents an evaluation of the intonation component of the text-to-phoneme system (TTS) developed at CSTR (McAllister & Shockey 1986). Lack of acoustic output obliges us to assess the performance of our intonation rules on the basis of the symbolic representation which they produce rather than any waveform which could be generated from this.
Cite as: Monaghan, A.I.C., Ladd, D.R. (1989) Evaluating intonation in the CSTR text-to-speech system. Proc. Speech Input/Output Assessment and Speech Databases, Vol.2, 111-114
@inproceedings{monaghan89_sioa,
author={Alex I. C. Monaghan and D. Robert Ladd},
title={{Evaluating intonation in the CSTR text-to-speech system}},
year=1989,
booktitle={Proc. Speech Input/Output Assessment and Speech Databases},
pages={Vol.2, 111-114}
}