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
Cite as: Saheer, L., Dines, J., Garner, P.N., Liang, H. (2010) Implementation of VTLN for statistical speech synthesis. Proc. 7th ISCA Workshop on Speech Synthesis (SSW 7), 224-229
@inproceedings{saheer10_ssw,
author={Lakshmi Saheer and John Dines and Philip N. Garner and Hui Liang},
title={{Implementation of VTLN for statistical speech synthesis}},
year=2010,
booktitle={Proc. 7th ISCA Workshop on Speech Synthesis (SSW 7)},
pages={224--229}
}