Amazigh Speech Recognition System Based on CMUSphinx

  • Meryam Telmem
  • Youssef Ghanou
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 37)


In this paper, we are proposing a new approach to build an Amazigh automated speech recognition system using Amazigh environment. This system is based on the open source CMU Sphinx-4, from the Carnegie Mellon University. CMU Sphinx is a large-vocabulary; speaker-independent, continuous speech recognition system based on discrete Hidden Markov Models (HMMs).


Speech recognition Amazigh language HMMs CMUSphinx-4 Artificial intelligence 


  1. 1.
    Lecouteux, B.: Reconnaissance automatique de la parole guidée par des transcriptions a priori. Doctoral thesis. Université d’Avignon (2008)Google Scholar
  2. 2.
    Satori, H., Harti, M., Chanfour, N.: Arabic speech recognition system based on CMUSphinx. IEEE. Program. I In: International Symposium on Computational Intelligence and Intelligent Informatics, ISCIII 2007 (2007).
  3. 3.
    Ghanou, Y., Bencheikh, G.: Architecture optimization and training for the multilayer perceptron using ant system. IAENG Int. J. Comput. Sci. 43(1), 20–26 (2016)Google Scholar
  4. 4.
    Douib, W.: Reconnaissance automatique de la parole arabe par cmu sphinx 4. Doctoral thesis. Université Ferhat Abbas de Sétif 1 (2013)Google Scholar
  5. 5.
  6. 6.
    Amour, M., Bouhjar, A., Boukhris, F.: 2004 IRCAM: publication: “initiation à la langue Amazigh” (2004)Google Scholar
  7. 7.
    El Ghazi, A., Daoui, C., Idrissi, N.: Automatic speech recognition system concerning the moroccan dialecte (darija and tamazight). Int. J. Eng. Sci. Technol. (IJEST), 2012, 4(3), 966–975 (2012). ISSN 0975-5462Google Scholar
  8. 8.
    Ulucinar, B.: Master thesis report (2007)Google Scholar
  9. 9.
    Carnegie Mellon University. Sphinx-4.
  10. 10.
    Alotaibi, Y.A.: Investigating spoken Arabic digits in speech recognition setting. Inf. Comput. Sci. 173, 115 (2005)Google Scholar
  11. 11.
  12. 12.
  13. 13.
  14. 14.
    Ettaouil, M., Ghanou, Y.: Neural architectures optimization and Genetic algorithms. Wseas Trans. Comput. 8(3), 526–537 (2009)Google Scholar
  15. 15.
    Kumar, K., Aggarwal, R.K., Jain, A.: A Hindi speech recognition system for connected words using HTK. Int. J. Comput. Syst. Eng. 1(1), 25–32 (2012)CrossRefGoogle Scholar
  16. 16.
    Abushariah, M.A.A.M., Ainon, R., Zainuddin, R., Elshafei, M., Khalifa, O.O.: Arabic speaker-independent continuous automatic speech recognition based on a phonetically rich and balanced speech corpus. Int. Arab J. Inf. Technol. (IAJIT) 9(1), 84–93 (2012)Google Scholar
  17. 17.
    Young, S.: The HTK hidden Markov model toolkit: design and philosophy. Doctoral thesis. Cambridge University Engineering Department, UK, Technical report. CUED/FINFENG/TR152, September 1994Google Scholar
  18. 18.
    Ali, A., Zhang, Y., Cakrdinal, P., Dahak, N., Vogel, S., Glass, J.: A complete kaldi recipe for building Arabic speech recognition systems. In: 2014 IEEE Spoken Language Technology Workshop (SLT), pp. 525–529. IEEE, December 2014Google Scholar
  19. 19.
    Satori, H., ElHaoussi, F.: Investigation Amazigh speech recognition using CMU tools. Int. J. Speech Technol. 17(3), 235–243 (2014)CrossRefGoogle Scholar
  20. 20.
    Al-Qatab, B.A.Q., Ainon, R.N.: Arabic speech recognition using Hidden Markov Model Toolkit (HTK). Paper presented at International Symposium in Information Technology (ITSim). Kuala Lumpur, 15–17 June (2010)Google Scholar
  21. 21.
    Ettaouil, M., Ghanou, Y., El Moutaouakil, K., Lazaar, M.: Image medical compression by a new architecture optimization model for the Kohonen networks. Int. J. Comput. Theory Eng. 3(2), 204–210 (2011)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Team TIM, High School of TechnologyMoulay Ismail UniversityMeknesMorocco

Personalised recommendations