Cascade–forward Neural Networks for Arabic Phonemes Based on k–Fold Cross Validation
DOI:
https://doi.org/10.11113/jt.v61.1630Keywords:
Cascade–forward network, nasal, lateral, trill, k–fold cross validationAbstract
The study of Malaysian Arabic phoneme is rarely found which make the references to the work is difficult. Specific guideline on Malaysian subject is not found even though a lot of acoustic and phonetics research has been done on other languages such as English, French and Chinese. In this paper, we monitored and analyzed the performance of cascade-forward (CF) networks on our phoneme recognition system of Standard Arabic (SA). This study focused on Malaysian children as test subjects. It is focused on four chosen phonemes from SA, which composed of nasal, lateral and trill behaviors, i.e. tabulated at four different articulation places. Cascade neural networks are chosen as it provide less time for samples processing. The method, k–fold cross validation to evaluate each network architecture in k times to improve the reliability of the choice of the optimal architecture. Based on this method, namely 10–fold cross validation, the most suitable cascade–layer network architecture in first hidden layer and second hidden layer is 40 and 10 nodes respectively with MSE 0.0402. The training and testing recognition rates achieved were 94% and 93% respectively.References
Z. J. Xiang, and G. Bi. 1990. A neural network model for Chinese speech synthesis. IEEE Int. Symp. on Circuits And Systems. 1859–1862.
P. G. J. Lisboa. 1992. Neural Networks Current Application. Chapman & Hall.
B. A. St. George, E. C. Wooten, and L. Sellami. 1999. Speech Coding and Phoneme Classification using Matlab and Neural Networks. Information Sciences Elsevier. 90: 109–119.
J. Frankel, K. Richmond, S. King, and P. Taylor. 2000. An Automatic Speech Recognition System using Neural Networks and Linear Dynamic Models to Recover and Model Articulatory Traces. Proceeding ICSLP.
H. N. Ting. 2002. Speech Analysis and Classification Using Neural Networks For Computer-based Malay Speech Therapy. Malaysia: UTM Malaysia.
C. L. Tan and A. Jantan. 2004. Digit Recognition Using Neural Networks. Malaysian Journal of Computer Science. 17(2): 40–54.
J. W. A.Fackrell, , H. Vereecken, J-P Martens, and B. V. Coile. 1999. Multilingual Prosody Modeling using Cascades Regression Trees and Neural Networks. Sixth European Conference on Speech Communication and Technology. 1835–1838.
B. Chandra and P. P. Varghese. 2007. Applications of Cascade Correlation Neural Networks for Cipher System Identification. World Academy of Science, Engineering and Technology 26. 312–314.
J. Macias-Guarasa, J. M. Montero, J. Ferreiros, R. Cordoba, R. San-Segundo, J. Gutierrez-Arriola, L. F. D'haro, F. Fernandez, R. Barra and J. M. Pardo. 2009. Novel Applications Of Neural Networks In Speech Technology Systems: Search Space Reduction And Prosodic Modeling. Intelligent Automation And Soft Computing. 15(4): 631–646.
L. R. Rabiner, and R. W. Schafer. 2007. Introduction to Digital Speech Processing, Foundations and Trends in Signal Processing Vol. 1 Issue 1-2. USA. The Essence of Knowledge.
N. K. Kasabov. 1996. Foundations of Neural Network, Fuzzy Systems, and Knowledge Engineering. 1996. London. The MIT Press Cambridge.
T. Andersen and T. Martinez. 1999. Cross Validation and MLP Architecture Selection. IEEE International Joint Conference on Neural Networks IJCNN’99. 3: 1614–1619 vol. 3.
J. L. Wright. 2010. Neural Network Architecture Selection Analysis with Application to Cryptography Location. IEEE World Congress on Computational Intelligence.
R. O. Duda, P. E. Hart and D. G. Stork. 2001. Pattern Classification. John-Wiley.
A. Hassan. 1984. Linguistik Am Untuk Guru Bahasa. Malaysia. Fajar Bakti.
L. Rabiner, and B. H. Juang. 1993. Fundamentals of Speech Recognition. Englewood Cliffs, New Jersey. Prentice Hall.
K. Johnson. 2003. Acoustic and Auditory Phonetics 3rd Edition. 2003. United Kingdom. Blackwell Publishing.
W. B. Al-Shargabi, Al-Romimah and F. Olayah. 2011. A Comparative study for Arabic text classification algorithms based on stop words elimination. Proceedings of International Conference on Intelligent Semantic Web-Services and Applications.
N. A. Abdul-Kadir and R. Sudirman. 2011. Difficulties of Standard Arabic Phonemes Spoken by Non-arab Primary School Children based on Formant Frequencies. J. Computer Science. 7: 1003–1010.
N. A. Abdul-Kadir, R. Sudirman, and N. M. Safri. 2010. Modeling of the Plosive Consonants Characteristics based on Spectrogram. Proceeding of the 4th Asia International Conference on Mathematical/Analytical Modeling and Computer Simulation. 282–285.
Downloads
Published
Issue
Section
License
Copyright of articles that appear in Jurnal Teknologi belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.
