HMM-Based Lightweight Speech Recognition System for Gujarati Language

  • Jinal H. Tailor
  • Dipti B. Shah
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 10)


Speech recognition system (SRS) is growing research interest in the area of natural language processing (NLP). To develop speech recognition system for low resource language is difficult task. This paper defines a lightweight speech recognition system approach for Indian Gujarati language using hidden Markov model (HMM). The aim of this research is to design and implement SRS for routine Gujarati language which is difficult due to language barrier, complex language framework, and morphological variance. To train the HMM-based SRS we have manually created speech corpora that contained 650 routine Gujarati utterances which are recorded from total 40 speakers of South Gujarat region. Total numbers of speakers are selected on the basis of gender. We have achieved accuracy of 87.23% with average error rate 12.7% based on the word error rate (WER) computing.


Gujarati language Hidden Markov model Speech recognition Word error rate (WER) 


  1. 1.
    Weischedel, R., Carbonell, J., Grosz, B., Lehnert, W., Marcus, M., Perrault, R., & Wilensky, R. (1989, October). White paper on natural language processing. In Proceedings of the workshop on Speech and Natural Language (pp. 481–493). Association for Computational Linguistics.Google Scholar
  2. 2.
    Sandanalakshmi, R., Viji, P. A., Kiruthiga, M., Manjari, M., & Sharina, M. (2013). Speaker Independent Continuous Speech to Text Converter for Mobile Application. arXiv preprint arXiv:1307.5736.
  3. 3.
    Uchat, N. S. (2007). Hidden Markov Model and Speech Recognition. In Seminar report, Department of Computer Science and Engineering Indian Institute of Technology, Mumbai.Google Scholar
  4. 4.
    Jain, D., & Cardona, G. (2007). The Indo-Aryan languages. Routledge.Google Scholar
  5. 5.
    Gales, M., & Young, S. (2008). The application of hidden Markov models in speech recognition. Foundations and trends in signal processing, 1(3), 195–304.Google Scholar
  6. 6.
    Samudravijaya, K. (1878). Computer recognition of spoken Hindi. training, 198(56), 93. Samudravijaya, K., Computer Recognition of Spoken Hindi‖. Proceeding of International Conference of Speech, Music and Allied Signal Processing, Triruvananthapuram, pages 8–13, 2000.Google Scholar
  7. 7.
    Samudravijaya, K., Ahuja, R., Bondale, N., Jose, T., Krishnan, S., Poddar, P., & Raveendran, R. (1998). A feature-based hierarchical speech recognition system for Hindi. Sadhana, 23(4), 313–340.Google Scholar
  8. 8.
    Kuldeep Kumar and R.K. Aggarwal, “hındı speech recognition system using HTK”, International Journal of Computing and Business Research, vol. 2, no. 2, 2011.Google Scholar
  9. 9.
    Kumar, M., Rajput, N., & Verma, A. (2004). A large-vocabulary continuous speech recognition system for Hindi. IBM journal of research and development, 48(5.6), 703–715.Google Scholar
  10. 10.
    Kumar, M., Aggarwal, R. K., Leekha, G., & Kumar, Y. (2012). Ensemble feature extraction modules for improved Hindi speech recognition system. Proc Int J Comput Sci, (9), 3.Google Scholar
  11. 11.
    Gaurav, G., Deiv, D. S., Sharma, G. K., & Bhattacharya, M. (2012). Development of application specific continuous speech recognition system in Hindi.Google Scholar
  12. 12.
    Thangarajan, R., Natarajan, A. M., & Selvam, M. (2008). Word and triphone based approaches in continuous speech recognition for Tamil language. WSEAS transactions on signal processing, 4(3), 76–86.Google Scholar
  13. 13.
    Das, B., Mandal, S., & Mitra, P. (2011, October). Bengali speech corpus for continuous automatic speech recognition system. In Speech Database and Assessments (Oriental COCOSDA), 2011 International Conference on (pp. 51–55). IEEE.Google Scholar
  14. 14.
    Udhyakumar, N., Swaminathan, R., & Ramakrishnan, S. K. (2004, May). Multilingual speech recognition for information retrieval in Indian context. In Proceedings of the Student Research Workshop at HLT-NAACL 2004 (pp. 1–6). Association for Computational Linguistics.Google Scholar
  15. 15.
    Lakshmi, A., & Murthy, H. A. (2008). A new approach to continuous speech recognition in Indian languages. In Proceedings national conference communication.Google Scholar
  16. 16.
    Dua, M., Aggarwal, R. K., Kadyan, V., & Dua, S. (2012). Punjabi automatic speech recognition using HTK. IJCSI International Journal of Computer Science Issues, 9(4), 1694–0814.Google Scholar
  17. 17.
    Aggarwal, R. K., & Dave, M. (2011). Using Gaussian mixtures for Hindi speech recognition system. International Journal of Signal Processing, Image Processing and Pattern Recognition, 4(4), 157–170.Google Scholar
  18. 18.
    Mishra, A. N., Chandra, M., Biswas, A., & Sharan, S. N. (2011). Robust features for connected Hindi digits recognition. International Journal of Signal Processing, Image Processing and Pattern Recognition, 4(2), 79–90.Google Scholar
  19. 19.
    Kumar, R., Kishore, S., Gopalakrishna, A., Chitturi, R., Joshi, S., Singh, S., & Sitaram, R. (2005). Development of Indian language speech databases for large vocabulary speech recognition systems. In International Conference on Speech and Computer (SPECOM) Proceedings.Google Scholar
  20. 20.
    Nilsson, M., & Ejnarsson, M. (2002). Speech recognition using hidden markov model.Google Scholar
  21. 21.
    Huang, X., & Deng, L. (2010). An Overview of Modern Speech Recognition.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.S.P. UniversityGujaratIndia
  2. 2.G.H. Patel Post Graduate Department of Computer ScienceS.P. UniversityGujaratIndia

Personalised recommendations