Rule Based Schwa Deletion Algorithm for Text to Speech Synthesis in Hindi

Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 27)


This paper provides the solution of Schwa deletion while converting grapheme into phoneme for Hindi language. Schwa is short neutral vowel and its sound depends onto adjacent consonant. Schwa deletion is a significant problem because while writing in Hindi every Schwa is followed by a consonant but during pronunciation, not every Schwa followed by a consonant is pronounced. In order to obtain good quality TTS system, it is necessary to identify which Schwa should be deleted and which should be retained. In this paper we provide various rules for Schwa deletion which are presently applicable to a limited length of word and will try to further extend it in future.


Schwa block phoneme vowel consonant 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Wasala, A., Weerasinghe, R., Gamage, K.: Sinhala Grapheme-to-Phoneme Conversion and Rules for Schwa Epenthesis. In: Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions, pp. 890–897 (2006)Google Scholar
  2. 2.
    Choudhury, M.: Rule-Based Grapheme to Phoneme Mapping for Hindi Speech Synthesis In: 90th Indian Science Congress of the International Speech Communication AssociationGoogle Scholar
  3. 3.
  4. 4.
    Narasimhan, B., Sproat, R., Kiraz, G.: Schwa-Deletion in Hindi Text-to-Speech Synthesis. International Journal Speech Technology 7(4), 319–333 (2004)CrossRefGoogle Scholar
  5. 5.
    Singh, P., Lehal, G.S.: A Rule Based Schwa Deletion Algorithm for Punjabi TTS System. In: Singh, C., Singh Lehal, G., Sengupta, J., Sharma, D.V., Goyal, V. (eds.) ICISIL 2011. CCIS, vol. 139, pp. 98–103. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  6. 6.
    Choudhury, M., Basu, A.: A rule based algorithm for Schwa deletion in Hindi. In: International Conf. on Knowledge-Based Computer Systems, pp. 343–353 (2002)Google Scholar
  7. 7.
    Jurafsky, D., Martin, J.H.: Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Pearson Education (2000)Google Scholar
  8. 8.
    Dabre, R., Amberkar, A., Bhattachrya, P.: A way to them all:A compound word analyzer for Marathi. In: ICON (2013)Google Scholar
  9. 9.
    Deepa, S.R., Bali, K., Ramakrishnan, A.G., Talukdar, P.P.: Automatic Generation of Compound Word Lexicon for Hindi Speech SynthesisGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringBanasthali UniversityTonkIndia

Personalised recommendations