Advertisement

Prosodic rules for schwa-deletion in hindi text-to-speech synthesis

  • Na’im R. Tyson
  • Ila Nagar
Article

Abstract

Consonants in written Hindi often carry annotations indicating the nature of the following vowel, which is not written separately. When there is no explicit marking, schwa is the default vowel, but this vowel does not always emerge in a word’s pronunciation. In addition, morphological boundaries can block the deletion of inherent schwas. Previous implementations of schwa deletion in the domain of text-to-speech synthesis (Narasimhan et al., International Journal of Speech Technology, 7(4):319–333, 2004; Choudhury and Basu, Proceedings of the International Conference on Knowledge-Based Computer Systems, 343–353, 2002) delete schwa in phonetic environments that obey the phonotactic constraints of Hindi within word boundaries. Instead of using segmental contexts, in conjunction with a morphological analysis, to predict schwa deletion, we used an account of syllable structure and stress assignment for two- and three-syllable words (Beckman and Pierrehumbert, forthcoming) to predict the presence and absence of schwa in a corpus of phonetically transcribed Hindi. Our algorithm scored as high as 95% accuracy on the deletion of schwa from a small corpus of Hindi words.

Keywords

Text-to-speech synthesis Speech synthesis Hindi schwa deletion Hindi prosody Hindi phonology 

References

  1. Bali, K., Talukdar, P. P., & Krishna, N. S. (2004). Tools for the development of a Hindi speech synthesis system. In 5th ISCA speech synthesis workshop (pp. 109–114). Google Scholar
  2. Beckman, M. E., & Pierrehumbert, J. B. (forthcoming). A laboratory course in phonology. Oxford: Blackwell. Google Scholar
  3. Bhaskararao, P., & Mathew, S. (1992). Phoemic transcription rules for text-to-speech synthesis of Hindi. In R. Sinha (Ed.), Computer processing of Asian languages (pp. 310–311). New Delhi: Tata McGraw-Hill. Google Scholar
  4. Bright, W. (1996). The world’s writing systems. New York: Oxford University Press (pp. 384–390). Google Scholar
  5. Chomsky, N., & Halle, M. (1968). The sound pattern of English. New York: Harper & Row. Google Scholar
  6. Choudhury, M., & Basu, A. (2002). A rule based schwa deletion algorithm for Hindi. In Proceedings of the international conference on knowledge-based computer systems (pp. 343–353). Navi Mumbai: Vikas Publishing House. Google Scholar
  7. Mohri, M., Pererira, F., & Riley, M. (1998). A rational design for a weighted finite-state transducer library. In D. Wood & S. Yu (Eds.), Automata implementation (pp. 144–158). Berlin: Springer. CrossRefGoogle Scholar
  8. Narasimhan, B., Sproat, R., & Kiraz, G. (2004). Schwa-deletion in Hindi text-to-speech synthesis. International Journal of Speech Technology, 7(4), 319–333. CrossRefGoogle Scholar
  9. Ohala, M. (1983). Aspects of Hindi phonology (Chaps. 4 and 6, pp. 37–76 and 117–154). Motilal Banarsidass. Google Scholar
  10. Pandey, P. K. (1990). Hindi schwa deletion. Lingua, 82, 277–311. CrossRefGoogle Scholar
  11. Pierrehumbert, J., & Nair, R. (1996). Implications of Hindi prosodic structure. Current Trends in Phonology: Models and Methods, 2, 549–584. Google Scholar
  12. Sharma, A. (1969). Hindi word-accent. Indian Linguistics, 30. Google Scholar
  13. Shukla, S. (1990). Syllable structure and word stress in Hindi. The Georgetown Journal of Languages & Linguistics, 1.2. Google Scholar
  14. Snell, R., & Weightman, S. (1992). Hindi: A complete course for beginners. NTC Publishing Group. Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  1. 1.Ohio State UniversityColumbusUSA

Personalised recommendations