The Effect of Using Normalized Models in Statistical Speech Synthesis

@inproceedings{Shannon2011TheEO,
  title={The Effect of Using Normalized Models in Statistical Speech Synthesis},
  author={Matt Shannon and Heiga Zen and William J. Byrne},
  booktitle={INTERSPEECH},
  year={2011}
}
The standard approach to HMM-based speech synthesis is inconsistent in the enforcement of the deterministic constraints between static and dynamic features. The trajectory HMM and autoregressive HMM have been proposed as normalized models which rectify this inconsistency. This paper investigates the practical effects of using these normalized models, and examines the strengths and weaknesses of the different models as probabilistic models of speech. The most striking difference observed is that… CONTINUE READING