ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

A decision tree-based clustering approach to state definition in an excitation modeling framework for HMM-based speech synthesis

Ranniery Maia, Tomoki Toda, Keiichi Tokuda, Shinsuke Sakai, Satoshi Nakamura

This paper presents a decision tree-based algorithm to cluster residual segments assuming an excitation model based on statedependent filtering of pulse train and white noise. The decision tree construction principle is the same as the one applied to speech recognition. Here parent nodes are split using the residual maximum likelihood criterion. Once these excitation decision trees are constructed for residual signals segmented by full context models, using questions related to the full context of the training sentences, they can be utilized for excitation modeling in speech synthesis based on hidden Markov models (HMM). Experimental results have shown that the algorithm in question is very effective in terms of clustering residual signals given segmentation, pitch marks and full context questions, resulting in filters with good residual modeling properties.


doi: 10.21437/Interspeech.2009-149

Cite as: Maia, R., Toda, T., Tokuda, K., Sakai, S., Nakamura, S. (2009) A decision tree-based clustering approach to state definition in an excitation modeling framework for HMM-based speech synthesis. Proc. Interspeech 2009, 1783-1786, doi: 10.21437/Interspeech.2009-149

@inproceedings{maia09_interspeech,
  author={Ranniery Maia and Tomoki Toda and Keiichi Tokuda and Shinsuke Sakai and Satoshi Nakamura},
  title={{A decision tree-based clustering approach to state definition in an excitation modeling framework for HMM-based speech synthesis}},
  year=2009,
  booktitle={Proc. Interspeech 2009},
  pages={1783--1786},
  doi={10.21437/Interspeech.2009-149}
}