Advertisement

Korean Grapheme to Phoneme Conversion Using Phonological Phrasing Information – Focused on Tensification

  • Byeongchang Kim
  • Jinsik Lee
  • Gary Geunbae Lee
Conference paper
  • 719 Downloads
Part of the Communications in Computer and Information Science book series (CCIS, volume 195)

Abstract

This paper proposes a grapheme to phoneme conversion method for Korean Text-to-Speech system where the phonological phrasing information is incorporated. To verify the validity of the proposing method, a hybrid approach based grapheme to phoneme conversion system, which combines hand-written morphophonemic rules and maximum entropy models, is implemented. The experimental results show that the prediction accuracy of tensification on the eojeol (a space-delimited orthographic word) boundaries improve from 93.20% to 95.45%, which leads to better overall grapheme to phoneme conversion performance.

Keywords

Korean grapheme to phoneme conversion phonological phrasing speech synthesis 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lee, J., Kim, S., Lee, G.G.: Grapheme-to-phoneme conversion using automatically extracted associative rules for Korean TTS system. In: Proc. of Interspeech 2006, Pittsburgh, pp. 1405–1408 (2006)Google Scholar
  2. 2.
    Taylor, P.: Hidden Markov model for grapheme to phoneme conversion. In: Proc. of Interspeech 2005, Lisbon, pp. 1973–1976 (2005)Google Scholar
  3. 3.
    King, R.: Korean writing. In: Daniels, P.T., Bright, W. (eds.) The World’s Writing Systems, pp. 218–227. Oxford University Press, Oxford (1996)Google Scholar
  4. 4.
    The National Institute of the Korean Language, 표준발음법 (Regulation of Standard Korean Pronunciation) (1998), http://www.korean.go.kr/
  5. 5.
    Yoon, K., Brew, C.: A linguistically motivated approach to grapheme-to-phoneme conversion for Korean. Computer Speech and Language 20(4), 357–381 (1996)CrossRefGoogle Scholar
  6. 6.
    Lee, J., Lee, G.G.: A data-driven grapheme-to-phoneme conversion method using dynamic contextual converting rules for Korean TTS systems. Computer Speech and Language 23(4), 423–434 (2009)CrossRefGoogle Scholar
  7. 7.
    Kim, B., Lee, G.G., Lee, J.-H.: Morpheme-based grapheme to phoneme conversion using phonetic patterns and morphophonemic connectivity information. ACM Trans. on Asian Language Information Processing 1(1), 65–82 (2002)CrossRefGoogle Scholar
  8. 8.
    Lee, J., Kim, B., Lee, G.G.: Hybrid approach to grapheme to phoneme conversion for Korean. In: Proc. of Interspeech 2009, Brighton, pp. 1291–1294 (2009)Google Scholar
  9. 9.
    Berger, A., Della Pietra, S., Della Pietra, V.: A maximum entropy approach to natural language processing. Computational Linguistics 22(1), 39–71 (1996)Google Scholar
  10. 10.
    Kang, O.: Korean Prosodic Phonology, Ph. D. Dissertation, University of Washington (1993)Google Scholar
  11. 11.
    Jun, S.: K-ToBI (Korean ToBI) labeling conventions (version 3.1), http://www.linguistics.ucla.edu/people/jun/ktobi/k-tobi.html

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Byeongchang Kim
    • 1
  • Jinsik Lee
    • 2
  • Gary Geunbae Lee
    • 2
  1. 1.School of Computer and Information Communication EngineeringCatholic University of DaeguSouth Korea
  2. 2.Department of Computer Science and EngineeringPohang University of Science and TechnologySouth Korea

Personalised recommendations