This paper is an initial investigation into using knowledge-based parameters in the field of statistical parametric speech synthesis (SPSS). Utilizing the types of speech parameters used in the Klatt Formant Synthesizer we present automatic techniques for deriving such parameters from a speech database and building a statistical parametric speech synthesizer from these derived parameters. Although the work is exploratory, it shows promise in using more speech production inspired parameterizations for statistical speech synthesis.
Index Terms: statistical speech synthesis, Klatt formant synthesizer.
Cite as: Anumanchipalli, G.K., Cheng, Y.-C., Fernandez, o., Huang, X., Mao, Q., Black, A.W. (2010) KLATTSTAT: knowledge-based parametric speech synthesis. Proc. 7th ISCA Workshop on Speech Synthesis (SSW 7), 206-210
@inproceedings{anumanchipalli10b_ssw,
author={Gopala Krishna Anumanchipalli and Ying-Chang Cheng and oseph Fernandez and Xiaohan Huang and Qi Mao and Alan W. Black},
title={{KLATTSTAT: knowledge-based parametric speech synthesis}},
year=2010,
booktitle={Proc. 7th ISCA Workshop on Speech Synthesis (SSW 7)},
pages={206--210}
}