Skip to main content
SpringerLink
Log in

Comparing ANN to HMM in implementing limited Arabic vocabulary ASR systems

  • Published:
International Journal of Speech Technology Aims and scope Submit manuscript

Abstract

In this paper we investigated Artificial Neural Networks (ANN) based Automatic Speech Recognition (ASR) by using limited Arabic vocabulary corpora. These limited Arabic vocabulary subsets are digits and vowels carried by specific carrier words. In addition to this, Hidden Markov Model (HMM) based ASR systems are designed and compared to two ANN based systems, namely Multilayer Perceptron (MLP) and recurrent architectures, by using the same corpora. All systems are isolated word speech recognizers. The ANN based recognition system achieved 99.5% correct digit recognition. On the other hand, the HMM based recognition system achieved 98.1% correct digit recognition. With vowels carrier words, the MLP and recurrent ANN based recognition systems achieved 92.13% and 98.06, respectively, correct vowel recognition; but the HMM based recognition system achieved 91.6% correct vowel recognition.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Abdulah, W., Abdul-Karim, M. (1985). Real-time spoken Arabic recognizer. International Journal of Electronics, 59(5), 645–648.

    Article  Google Scholar 

  • Alghamdi, M. M. (1998). A spectrographic analysis of Arabic vowels: a cross-dialect study. Journal of King Saud University, 10(Arts1), 3–24.

    MathSciNet  Google Scholar 

  • Alghamdi, M. (2001). Arabic phonetics. Riyadh: Al-Toubah Bookshop (in Arabic).

    Google Scholar 

  • Alkhouli, M. (1990). Alaswaat Alaghawaiyah. Daar Alfalah: Jordan (in Arabic).

    Google Scholar 

  • Alotaibi, Y. A. (2003). High performance Arabic digits recognizer using neural networks. In The 2003 international joint conference on neural networks—IJCNN2003, Portland, Oregon.

    Google Scholar 

  • Deller, J., Proakis, J., & Hansen, J. H. (1993). Discrete-time processing of speech signal. New York: Macmillan Co.

    Google Scholar 

  • El-Imam, Y. A. (1989). An unrestricted vocabulary Arabic speech synthesis system. IEEE Transactions on Acoustics, Speech, and Signal Processing, 37(12), 1829–1845.

    Article  Google Scholar 

  • Elshafei, M. (1991). Toward an Arabic text-to-speech system. The Arabian Journal for Science and Engineering, 16(4B), 565–583.

    MathSciNet  Google Scholar 

  • Hagos, E. (1985). Implementation of an isolated word recognition system. UMI Dissertation Service.

  • Haykin, S. (1999). Neural networks: a comprehensive foundation (2nd ed.). New York: Prentice Hall.

    MATH  Google Scholar 

  • Iqbal, H. R., Awais, M. M., Masud, S., & Shamail, S. (2008). On vowels segmentation and identification using formant transitions in continuous recitation of Quranic Arabic. In New challenges in applied intelligence technologies (pp. 155–162) Berlin: Springer.

    Chapter  Google Scholar 

  • Juang, B., & Rabiner, L. (1991). Hidden Markov models for speech recognition. Technometrics, 33(3), 251–272.

    Article  MathSciNet  MATH  Google Scholar 

  • Kirchhoff, K., Bilmes, J., Das, S., Duta, N., Egan, M., Gang, J., Feng, H., Henderson, J., Daben, L., Noamany, M., Schone, P., Schwartz, R., & Vergyri, D. (2003). Novel approaches to Arabic speech recognition: report from the 2002 Johns-Hopkins Summer Workshop. In Proceedings of ICASSP 2003, April 2003 (Vol. 1, pp. 344–347).

    Google Scholar 

  • Linguistic Data Consortium (LDC) (2002). Catalog number LDC2002S02, http://www.ldc.upenn.edu/.

  • Lippmann, R. (1989). Review of neural networks for speech recognition. Neural computation (pp. 1–38). Cambridge: MIT Press.

    Google Scholar 

  • Loizou, P. C., & Spanias, A. S. (1996). High-performance alphabet recognition. IEEE Transactions on Speech and Audio Processing, 4(6), 430–445.

    Article  Google Scholar 

  • Newman, D. L., & Verhoeven, J. (2002). Frequency analysis of Arabic vowels in connected speech. Antwerp Papers in Linguistics, 100, 77–87.

    Google Scholar 

  • Omar, A. (1991). Derasat Alaswat Aloghawi. Egypt: Aalam Alkutob (in Arabic).

    Google Scholar 

  • Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257–286.

    Article  Google Scholar 

  • Razak, Z., Ibrahim, N. J., Tamil, E. M., Idris, M. Y. I., Yakub, M., & Yusoff, Z. B. M. (2008). Quranic verse recitation feature extraction using mel-frequency cepstral coefficient (MFCC). In Proceedings of the 4th IEEE international colloquium on signal processing and its application (CSPA), 7–9 March 2008, Kuala Lumpur, Malaysia.

    Google Scholar 

  • Tolba, M. F., Nazmy, T., Abdelhamid, A. A., & Gadallah, M. E. (2005). A novel method for Arabic consonant/vowel segmentation using wavelet transform. International Journal on Intelligent Cooperative Information Systems, IJICIS, 5(1), 353–364.

    Google Scholar 

  • Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., & Woodland, P. (2006). The HTK book (for HTK version. 3.4). Cambridge: Cambridge University Engineering Department. http:///htk.eng.cam.ac.uk/prot-doc/ktkbook.pdf.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer Engineering Dept., College of Computer & Information Sciences, King Saud University, P.O. Box 57168, Riyadh, 11574, Saudi Arabia

    Yousef Ajami Alotaibi

Authors
  1. Yousef Ajami Alotaibi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yousef Ajami Alotaibi.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Alotaibi, Y.A. Comparing ANN to HMM in implementing limited Arabic vocabulary ASR systems. Int J Speech Technol 15, 25–32 (2012). https://doi.org/10.1007/s10772-011-9107-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10772-011-9107-3

Keywords

Search

Navigation