Skip to main content

Speech recognition for knowledge based computer systems

  • Activities At The KBCS Nodal Centres
  • Conference paper
  • First Online:
  • 1951 Accesses

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 444))

Abstract

The Knowledge Based Computer Systems project at the Tata Institute of Fundamental Research (TIFR) aims to make a concerted effort for research in the area of computer speech recognition in the context of Indian languages. For this, four approaches have been identified, namely the subword unit analysis, hidden Markov models, acoustic-phonetic feature analysis and artificial neural networks. This paper presents each of these approaches briefly and discusses the merits and demerits of each of these approaches. The activities related to the project as well as the work under way at TIFR in each of these approaches is also discussed. It is seen that the four approaches considered in this paper complement each other and may be used in conjunction with each other to improve the performance of speech recognition systems.

uunet!shakti!tifr!csc11

This is a preview of subscription content, log in via an institution.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Krishnan S and Poddar P. A probabilistic training scheme for the time concentration network. Proc. of KBCS conference, Bombay, Dec. 1989.

    Google Scholar 

  2. Levinson SE. Structural methods in automatic speech recognition. Proc. IEEE, 73, pp.1625–1650, 1985.

    Google Scholar 

  3. Rumelhart DE, McClelland JL and the PDP research group Parallel Distributed Processing. Explorations in the microstructure of cognition. MIT Press, 1986.

    Google Scholar 

  4. Wilpon JG, Juang BH and Rabiner LR. An investigation on the use of acoustic sub-word units for automatic speech recognition. Proc. ICASSP, 20.7.1–20.7.4, pp. 821–824, 1987.

    Google Scholar 

  5. Unnikrishnan KP. Personal communication.

    Google Scholar 

  6. Zue VW. The use of speech specific knowledge in automatic speech recognition. Proc. IEEE 73, pp. 1602–1615, 1985.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

S. Ramani R. Chandrasekar K. S. R. Anjaneyulu

Rights and permissions

Reprints and permissions

Copyright information

© 1990 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Rao, P., Krishnan, S., Poddar, P., Ramasubramanian, V., Samudravijaya, K., Sen, A. (1990). Speech recognition for knowledge based computer systems. In: Ramani, S., Chandrasekar, R., Anjaneyulu, K.S.R. (eds) Knowledge Based Computer Systems. KBCS 1989. Lecture Notes in Computer Science, vol 444. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0018410

Download citation

  • DOI: https://doi.org/10.1007/BFb0018410

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-52850-0

  • Online ISBN: 978-3-540-47168-4

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics