Tamil Speech Recognizer Using Hidden Markov Model for Question Answering System of Railways

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 325)


The research on speech and natural language is in progress for more than two decades. Recently, researchers are focused on developing speech interfaces to their corresponding automated system. For voice-based question answering system, there is the need for developing speech recognizer. Although automatic speech recognition (ASR) systems are already available, most of them have been built for English language. This paper aims to build Tamil speech recognizer for question answering system of railway information using natural language processing. Most feasible approach for speech recognition so far has been hidden Markov model (HMM) which is implemented in this research work. HMM-based recognition component is trained automatically and computationally realistic to use. The recognition accuracy of the system using HMM has up to 85 % for different speakers.


Automatic speech recognition Hidden Markov model Voice recording Word boundary detections Session initiation protocol 


  1. 1.
    S. Saraswathi, T. Geetha, Morpheme based language model for Tamil speech recognition system. Int. Arab J. Inf. Technol. 4(3), 214–219 (2007)Google Scholar
  2. 2.
    D. Sharmila et al., Performance of Hindi speech isolated digits in HTK environment. IOSR J. Eng. 2(5), 1020–1023 (2012)Google Scholar
  3. 3.
    C. Vimala, V. Radha, A review on speech recognition challenges and approaches. World Comput. Sci. Inf. Technol. J. (WCSIT) 2(1), 1–7 (2012)Google Scholar
  4. 4.
    R. Thangarajan et al., Syllable modeling in continuous speech recognition for Tamil language. Int. J. Speech Technol. 12(1), 47–57 (2009)CrossRefGoogle Scholar
  5. 5.
    M. Chandrasekar, M. Ponnavaikko, Tamil speech recognition: a complete model. Electron. J. Tech. Acoust. 20 (2008)Google Scholar
  6. 6.
    K. Shyam, SHARIKA malayalam speech recognition system, in International Conference ICIST2007 (2007)Google Scholar
  7. 7.
    L.R. Rabiner, A tutorial on hidden markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257–286 (1989)CrossRefGoogle Scholar
  8. 8.
    L.R. Bahl et al., A tree-based statistical language model for natural language speech recognition. IEEE Trans. Acoust. Speech, Sig. Process. 37, 1001–1008 (1989)CrossRefGoogle Scholar
  9. 9.
    H. Gnanathesigar, Tamil speech recognition using semi continuous models. Int. J. Sci. Res. Publ. 2(6) (2012)Google Scholar
  10. 10.
    P. Ross et al, On the voice-activated question answering. IEEE Trans. Syst. Man Cybern. 42(1) (2012)Google Scholar
  11. 11.
    A. Srinivasan et al., Speech recognition of the letter ‘zha’ (H) in Tamil language using HMM. Int. J. Eng. Sci. Technol. 1(2), 67–72 (2009)Google Scholar

Copyright information

© Springer India 2015

Authors and Affiliations

  1. 1.Department of Information TechnologyNational Engineering CollegeKovilpattiIndia

Personalised recommendations