Abstract:
The paper describes a method for evaluating the quality of synthetic intonation using subjective techniques. This perceptual method of assessing intonation, not only eval...Show MoreMetadata
Abstract:
The paper describes a method for evaluating the quality of synthetic intonation using subjective techniques. This perceptual method of assessing intonation, not only evaluates the quality of synthetic intonation, but also allows us to compare different models of intonation to know which one is the most natural from a perceptual point of view. This procedure has been used to assess the quality of an implementation of Fujisaki's intonation model (Fujisaki, H. and Hirose, K., 1984) for the Basque language (Navas, E. et al., 2000). The evaluation involved 30 participants and results show that the intonation model developed has introduced a considerable improvement and that the overall quality achieved is good.
Date of Conference: 13-13 September 2002
Date Added to IEEE Xplore: 26 August 2003
Print ISBN:0-7803-7395-2
References is not available for this document.
Contents Select All
1.
K. Morton, “Expectations for Assessment Techniques Applied to Speech Synthesis ”, Proceedings of the Institute of Acoustics, Vol. 13, 1991.
2.
A. Di Cristo, P. Di Cristo, J. Véronis and E. Campione, “A model of prosody for French text-to-speech synthesis ”, Intonation: Models and Theories, Kluwer Academic Publishers, Berlin, pp. 321–355, 2000.
3.
A. Fourcin, “Assessment of synthetic speech ”, Talking Machines: Theories, Models and Designs. Elsevier Science, Amsterdam, pp. 431–434, 1992.
4.
D. Hirst, A. Rilliard, and V. Aubergé “Comparison of subjective evaluation and an objective evaluation metric for prosody in text-to-speech synthesis ”, 3rd ESCA/COCOSDA Workshop on Speech Synthesis, Blue Mountain, Australia, 1–4, 1998.
5.
R. A. J. Clark, and K. E. Dusterhoff, “Objective methods for evaluating synthetic intonation ”, Eurospeech99, Budapest, pp. 1623–1626, 1999.
6.
ITU-T Recommendationp P. 85, “A method for subjective performance assessment of the quality of speech voice output devices ”, study group 12, 1994.
7.
H. Fujisaki, and K. Hirose, “Analysis of voice fundamental frequency contours for declarative sentences of Japanese ”, Journal of Acoustic Society. Jpn. (E) 5, 4, 1984.
8.
E. Navas, I. Hernáez A. Armenta, B. Etxebarria, and J. Salaberria, “Modelling Basque intonation using Fujisakis models and CARTs ”, State of the art in Speech Synthesis digest, London, 3/1–3/6, 2000.
9.
I. Hernáez E. Navas, J. L. Murugarren, and B. Etxebrria, “Description of the AhoTTS System for Basque Language ”, 4th ISCA Tutorial Research Workshop on Speech Synthesis, Edinburgh, pp. 151–154, 2001.
10.
H. Mixdorff, and D. Mehnert, “Exploring the Naturalness of Several German High-Quality-Text-to-Speech Systems ”, Eurospeech99, Budapest, pp. 1859–1862, 1999.
