Automatic segmentation combining an HMM-based approach and spectral boundary correction

  title={Automatic segmentation combining an HMM-based approach and spectral boundary correction},
  author={Yeon-Jun Kim and Alistair Conkie},
Currently, AT&T Labs’ Natural Voices multilingual TTS system produces high-quality synthetic speech with a largescale speech corpus [1]. In the development of such systems, automatic segmentation constitutes a major component technology. The prevalent approach for automatic segmentation in speech synthesis is Hidden Markov Model (HMM) based. Even though an HMM-based approach is the most automatic and reliable, there are still several limitations, such as mismatches between hand-labeled… CONTINUE READING
Highly Cited
This paper has 90 citations. REVIEW CITATIONS
60 Citations
5 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 60 extracted citations

91 Citations

Citations per Year
Semantic Scholar estimates that this publication has 91 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-5 of 5 references

Perceptual Evaluation of tomatic Segmentation in Text-to-Speech Synthesis,

  • atthew J. Makashay, Colin W. Wightman, Ann K. rdal, Alistair Conkie
  • Proc. ICSLP 2000, Beijing,
  • 2000

dro Carvalho , Isabel Trancoso , and Luı́s Oliveira , utomatic Segmentation Alignment for Concatenative eech Synthesis in Portuguese

  • Richard W. Sproat
  • Proc . of EUSPEECH ’ 99

Similar Papers

Loading similar papers…