An HMM-based Vietnamese speech synthesis system

@article{Vu2009AnHV,
  title={An HMM-based Vietnamese speech synthesis system},
  author={Thang T. Vu and Mai Chi Luong and Satoshi Nakamura},
  journal={2009 Oriental COCOSDA International Conference on Speech Database and Assessments},
  year={2009},
  pages={116-121}
}
This paper describes an approach to the realization of a Vietnamese speech synthesis system applying a technique whereby speech is directly synthesized from Hidden Markov models (HMMs). Spectrum, pitch, and phone duration are simultaneously modeled in HMMs and their parameter distributions are clustered independently by using decision tree-based context clustering algorithms. Several contextual factors such as tone types, syllables, words, phrases, and utterances were determined and are taken… CONTINUE READING