Biologically inspired Continuous Arabic Speech Recognition

  • N. Hmad
  • T. Allen
Conference paper


Despite many years of research into speech recognition systems, there are limited research publications available covering Arabic speech recognition. Although statistical techniques have been the most applied techniques for such classification problems, Neural Networks have also recorded successful results in speech recognition. In this research three different biologically inspired Continuous Arabic Speech Recognition neural network system structures are presented. An Arabic phoneme database (APD) of six male speakers was constructed manually from the King Abdulaziz Arabic Phonetics Database (KAPD). The Mel-Frequency Cepstrum Coefficients (MFCCs) algorithm was used to extract the phoneme features from the speech signals of this database. The normalized dataset was used to train and test three different architectures of Multilayer Perceptron (MLP) neural network identification systems.


Speech Recognition Speech Signal Speech Recognition System Echo State Network Continuous Speech Recognition 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Yuk D.: Robust speech recognition using neural networks and hidden markov modelsadaptations using non-linear transformations [dissertation]. New Jersey: The State University of New Jersey; 1999.Google Scholar
  2. 2.
    Tursun, N., Silamu, W. In: Large vocabulary continuous speech recognition in uyghur: Data preparation and experimental results. Network computing and information security (NCIS), international conference; China. ; 2011. p. 197-200. N. Hmad and T. AllenGoogle Scholar
  3. 3.
    Al-manie, M.A., Alkanhal, M.I., Al-ghamdi, M.M. In: Automatic speech segmentation using the arabic phonetic database. Proceedings of the 10th WSEAS international conference on AUTOMATION & INFORMATION; ; 2006. p. 76-9.Google Scholar
  4. 4.
    Renals, S.: Radial Basis Function Network For Speech Pattern Classification. [Internet]. 1989;25(7):437; 439. Available from: internal-pdf://18-0638587909/18.pdf.Google Scholar
  5. 5.
    Maheswari, N.U., Kabilan, A.P., Venkatesh R.: Speaker independent phoneme recognition using neural networks. Journal of Theoretical and Applied Information Technology (JATIT). 2009:230-5.Google Scholar
  6. 6.
    Chen, W., Chen, S., Lin, C.: A speech recognition method based on the sequential multi-layer perceptrons. Neural Networks. 1996;9(4):655-69.CrossRefGoogle Scholar
  7. 7.
    Alghmadi, M.M.: KACST arabic phonetics database. Congress of Phonetics Sci. 2003;15:3109-12.Google Scholar
  8. 8.
    Mosa, G.S., Ali, A.A.: Arabic phoneme recognition using hierarchical neural fuzzy petri net and LPC feature extraction. Signal Processing: An International Journal (SPIJ). 2009;3(5):161-71.Google Scholar
  9. 9.
    Anwar, M.J., Awais, M.M., Masud, S., Shamail, S.: Automatic arabic speech segmentation system. International Journal of Information Technology. 2006;12(6):102-11.Google Scholar
  10. 10.
    Waheed, K., Weaver, K., Salam, F.M.: A robust algorithm for detecting speech segments using an entropic contrast. In proc. of the IEEE Midwest Symposium on Circuits and Systems. Lida Ray Technologies Inc. 2002;45.Google Scholar
  11. 11.
    Hong, L., Yanmin, Q., Jia, L.: English speech recognition system on chip. Tsinghua Science & Technology. 2011;16(1):95-9.CrossRefGoogle Scholar
  12. 12.
    Reynolds, T.J., Antoniou, C.A.: Experiments in speech recognition using a modular MLP architecture for acoustic modelling. Information Sciences. 2003;156(1-2):39-54.CrossRefGoogle Scholar
  13. 13.
    Jou, S., Schultz, T., Walliczek, M., Kraft, F., Waibel, A.: Towards continuous speech recognition using surface electromyography. Interspeech. 2006:573-6.Google Scholar
  14. 14.
    Kirchhoff, K., Vergyri, D.: Cross-dialectal data sharing for acoustic modeling in arabic speech recognition. Speech Communication. 2005;46(1):37-51.CrossRefGoogle Scholar
  15. 15.
    Szczurowska, I., Kuniszyk-Jókowiak, W., Smoka, E.: The application of kohonen and multilayer perceptron networks in the speech nonfluecy analysis. Archives of Acoustics. 2006;31(4):205-10.Google Scholar
  16. 16.
    Nakamura, M., Tsuda, K., Aoe, J.: A new approach to phoneme recognition by phoneme filter neural networks. Information Sciences. 1996;90(1-4):109-19.CrossRefGoogle Scholar
  17. 17.
    Koizumi, T., Mori, M., Taniguchi, S., Maruya, M. In: Recurrent neural networks for phoneme recognition. Department of information science, fourth international conference; 3- 6 Oct 1996; Fukui University, Fukui, Japan. Spoken Language, ICSLP 96; 1996. p. 326-9.Google Scholar
  18. 18.
    Skowronski, M.D., Harris, J.G.: Automatic speech recognition using a predictive echo state network classifier. Neural Networks. 2007;20(3):414-23.zbMATHCrossRefGoogle Scholar
  19. 19.
    Ismail, S., Bin Ahmad, A.M. In: Recurrent neural network with backpropagation through time algorithm for arabic recognition. ; 2004.Google Scholar
  20. 20.
    Bengio, Y.: Neural Networks For Speech And Sequence Recognition. first edition ed. International Thomson Computer Press; 1996.Google Scholar
  21. 21.
    Sweeney, L., Thompson, P.: Speech perception using real-time phoneme detection: The BeBe system. Laboratory for Computer Science, Massachusetts Institute of Technology, Cambridge, MA 02139, USA; 1997.Google Scholar

Copyright information

© Springer-Verlag London 2012

Authors and Affiliations

  1. 1.Nottingham Trent UniversityNottinghamUK

Personalised recommendations