Reversible Sound-to-Letter/Letter-to-Sound Modeling Based on Syllable Structure

@inproceedings{Seneff2007ReversibleSM,
  title={Reversible Sound-to-Letter/Letter-to-Sound Modeling Based on Syllable Structure},
  author={Stephanie Seneff},
  booktitle={HLT-NAACL},
  year={2007}
}
This paper describes a new grapheme-tophoneme framework, based on a combination of formal linguistic and statistical methods. A context-free grammar is used to parse words into their underlying syllable structure, and a set of subword “spellneme” units encoding both phonemic and graphemic information can be automatically derived from the parsed words. A statistical -gram model can then be trained on a large lexicon of words represented in terms of these linguistically motivated subword units… CONTINUE READING
13 Citations
8 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-8 of 8 references

Comparative evaluation of letter-to-sound conversion techniques for English text-to-speech synthesis

  • M. J. Adamson R.I. Damper, Y. Marchand, K. Gustafson.
  • Proc. IWSS, pages 53–58, Jenolan Caves, Australia…
  • 1998

The syllable in phonological theory

  • J. Blevins.
  • J. Goldsmith, Ed., the Handbook of Phonological…
  • 1995
1 Excerpt

Similar Papers

Loading similar papers…