Hidden Markov Models based text-to-speech (HMM-TTS) synthesis is a technique for generating speech from trained statistical models where spectrum, pitch and durations of basic speech units are modelled altogether. The aim of this work is to describe a Spanish HMM-TTS system using CBR as a F0 estimator, analysing its performance objectively and subjectively. The experiments have been conducted on a reliable labelled speech corpus, whose units have been clustered using contextual factors according to the Spanish language. The results show that the CBR-based F0 estimation is capable of improving the HMM-based baseline performance when synthesizing nondeclarative short sentences and reduced contextual information is available.
Cite as: Gonzalvo, X., Iriondo, I., Socoró, J.C., Alías, F., Monzo, C. (2007) HMM-based Spanish speech synthesis using CBR as F0 estimator. Proc. ITRW on Nonlinear Speech Processing (NOLISP 2007), 7-10
@inproceedings{gonzalvo07_nolisp,
author={Xavi Gonzalvo and Ignasi Iriondo and Joan Claudi Socoró and Francesc Alías and Carlos Monzo},
title={{HMM-based Spanish speech synthesis using CBR as F0 estimator}},
year=2007,
booktitle={Proc. ITRW on Nonlinear Speech Processing (NOLISP 2007)},
pages={7--10}
}