The Seventh ISCA Tutorial and Research Workshop on Speech Synthesis

Kyoto, Japan
September 22-24, 2010

Implementation of VTLN for Statistical Speech Synthesis

Lakshmi Saheer (1,2), John Dines (1), Philip N. Garner (1), Hui Liang (1,2)

(1) Idiap Research Institute, Martigny, Switzerland
(2) Ecole Polytechnique F´ed´erale de Lausanne, Switzerland

Vocal tract length normalization is an important feature normalization technique that can be used to perform speaker adaptation when very little adaptation data is available. It was shown earlier that VTLN can be applied to statistical speech synthesis and was shown to give additive improvements to CMLLR. This paper presents an EM optimization for estimating more accurate warping factors. The EM formulation helps to embed the feature normalization in the HMM training. This helps in estimating the warping factors more efficiently and enables the use of multiple (appropriate) warping factors for different state clusters of the same speaker.

Index Terms: Vocal tract length normalization, Expectation Maximization Optimization, HMM Synthesis, Adaptation

Full Paper

Bibliographic reference.  Saheer, Lakshmi / Dines, John / Garner, Philip N. / Liang, Hui (2010): "Implementation of VTLN for statistical speech synthesis", In SSW7-2010, 224-229.