Exploiting Prosody Hierarchy and Dynamic Features for Pitch Modeling and Generation in HMM-Based Speech Synthesis

@article{Hsia2010ExploitingPH,
  title={Exploiting Prosody Hierarchy and Dynamic Features for Pitch Modeling and Generation in HMM-Based Speech Synthesis},
  author={Chi-Chun Hsia and Chung-Hsien Wu and Jung-Yun Wu},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
  year={2010},
  volume={18},
  pages={1994-2003}
}
This paper proposes a method for modeling and generating pitch in hidden Markov model (HMM)-based Mandarin speech synthesis by exploiting prosody hierarchy and dynamic pitch features. The prosodic structure of a sentence is represented by a prosody hierarchy, which is constructed from the predicted prosodic breaks using a supervised classification and regression tree (S-CART). The S-CART is trained by maximizing the proportional reduction of entropy to minimize the errors in the prediction of… CONTINUE READING
Highly Cited
This paper has 45 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 34 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 39 references

TH-CoSS, a Mandarin speech corpus for TTS

  • L. H. Cai, D. D. Cui, R. Cai
  • J. Chinese Inf. Process., vol. 21, no. 2, pp. 94…
  • 2007
2 Excerpts

Similar Papers

Loading similar papers…