Double-stage features extraction for MALAY vowel classification using multinomial logistic regression

Authors

  • Yusof SAM School of Computing, College of Arts and Sciences, Universiti Utara Malaysia, Sintok, Kedah, Malaysia
  • Mahat NI Centre for Testing, Measurement, and Appraisal, School of Quantitative, College of Arts and Sciences, Universiti Utara Malaysia, Sintok, Kedah Malaysia
  • Husni H School of Computing, College of Arts and Sciences, Universiti Utara Malaysia, Sintok, Kedah, Malaysia
  • Atanda AF School of Computing, College of Arts and Sciences, Universiti Utara Malaysia, Sintok, Kedah, Malaysia

Keywords:

Malay vowels recognition, multinomial logistic regression, automatic speech recognition, accuracy

Abstract

Automatic speech recognition (ASR) has recorded enormous development in both research and implementation such as voice commands to control electronic appliances, video games, interface to voice dictation, assistive leaving for the elderly, and dialogue systems. Rapid development on ASR can be seen on English language, while duplicating the ASR framework for Malay language is possible, but the work demands for endlessly efforts. One of common tools that is able to classify Malay vowels is Multinomial Logistic Regression (MLR). However, careless on estimating the parameters of MLR may lead to producing biased classifier which inappropriate for future classification. Besides, the used on huge number of features for classification sometimes hinder MLR to perform well. This paper outlines a new idea for estimating the unknown MLR parameters with less number of features using a double-stage features extraction based on MLR (DSFE-MLR). The proposed DSFE-MLR extracted 39-MFCC from speech waveform and constructed an MLR using training set. Next, the MLR output of class membership probabilities were further extracted through MLR and evaluated using test set. Empirical evidence on Malay sample of students shows that the DSFE-MLR recorded the highest accuracy compared to other classifiers. Besides, the method is able to recognize each of five Malay vowels correctly. In general, DSFE-MLR provides increment of accuracy for Malay speech recognition.

References

A Genkin, D D Lewis, and D Madigan. (2007). Large-scale Bayesian Logistic Regression for text categorization. Technometrics, 49(3), 291-304. doi: 10.1198/004017007000000245

Arifin, N. ‘, &Tiun, S. (2013). Predicting Malay Prominent Syllable Using Support Vector Machine. Procedia Technology,11, 861-869.

doi:10.1016/j.protcy.2013.12.269

Azmi, M. S. (2016). Development of Malay Word Pronunciation Application using Vowel Recognition. International Journal of Uand E- Service, Science and Technology,9(1), 221-234. doi:10.14257/ijunesst.2016.9.1.24

Azmi, M. Y. S., Idayu, M. N., Roshidi, D., Yaakob, A., &Yaacob, S. (2012). Noise Robustness of Spectrum Delta (SpD) Features in Malay Vowel Recognition Computer Applications for Communication, Networking, and Digital Contents (pp. 270-277): Springer.

Azmi, S. (2010). Feature extraction and classification of malay speech vowels. Universiti Malaysia Perlis.

Azmi, S., Siraj, F., Yaacob, S., Paulraj, M., &Nazri, A. (2010). Improved Malay Vowel Feature Extraction Method Based on First and Second Formants. Paper presented at the Computational Intelligence, Modelling and Simulation (CIMSiM), 2010 Second International Conference on.

B H Juang, W Chou, and C H Lee. (1997). Minimum classification error rate methods for speech classification. IEEE Transactions on

Speech and Audio Processing, 5(3), 257-265. doi: 10.1109/89.568732

Lim, C. P., Woo, S. C., Loh, A. S., & Osman, R. (2000). Speech recognition using artificial neural networks. Paper presented at the WebInformation Systems Engineering, 2000. Proceedings of the First International Conference on.

Mazenan, M. N., & Tan, T. (2014). Malay Wordlist Modeling for Articulation Disorder Patient by Using Computerized Speech Diagnosis System. Research Journal of Applied Sciences, Engineering and Technology,7(21), 4535-4540. doi:10.19026/rjaset.7.830

Mohd Yusof, S. A. (2014). An improved feature extraction method for Malay vowel recognition based on spectrum delta. International

Journal of Software Engineering and Its Applications, 8(1), 413-426.

Mohd Yusof, S. A., Yaacob, S., &Paulraj, M. (2009). Vowel recognition using First Formant Feature.

Mohd Yusof, S., &Yaacob, S. (2008). Classification of Malaysian vowels using formant based features. Journal of ICT, 7, 27-40.

Rahman, F. D., Mohamed, N., Mustafa, M. B., & Salim, S. S. (2014). Automatic speech recognition system for Malay speaking children. 2014 Third ICT International Student Project Conference (ICT-ISPC). doi:10.1109/ict-ispc.2014.6923222

Singh, A., & Deep, A. (2011). Piperine: a bioenhancer. International Journal of Pharmacy Research and Technology, 1(1), 01-05.

Tan, T., Goh, S., &Khaw, Y. (2012). A Malay Dialect Translation and Synthesis System: Proposal and Preliminary System. 2012 International Conference on Asian Language Processing. doi:10.1109/ialp.2012.14

Ting, H. N., & Lam, Y. (2009). Speaker-Independent Malay Vowel Recognition of Children Using Neural Networks. Paper presented at

the World Congress on Medical Physics and Biomedical Engineering, September 7-12, 2009, Munich, Germany.

Ting, H. N., & Mark, K. (2008). Speaker-dependent Malay Vowel Recognition for a child with articulation disorder using multi-layer perceptron. Paper presented at the 4th Kuala Lumpur International Conference on Biomedical Engineering 2008.

Ting, H. N., &Yunus, J. (2004). Speaker-independent Malay vowel recognition of children using multi-layer perceptron. Paper presented at the TENCON 2004. 2004 IEEE Region 10 Conference.

Ting, H. N., Chia, S. Y., Hamid, B. A., &Mukari, S. Z.-M. S. (2011). Acoustic characteristics of vowels by normal Malaysian Malay young adults. Journal of Voice, 25(6), e305-e309.

Ting, H., &Zourmand, A. (2011). Gender Identification by Using Fundamental and Formant Frequency for Malay Children. Paper presented at the 5th Kuala Lumpur International Conference on Biomedical Engineering 2011.

J., Yakubu H., Aboiyar T., and Zirra P. B.. "An improved RSA image encryption algorithm using 1-D logistic map." International Journal of Communication and Computer Technologies 6 (2018), 1-6.

Downloads

Published

2024-02-26

How to Cite

Yusof, S. A. M., Mahat, N. I., Husni, H., & Atanda, A. F. (2024). Double-stage features extraction for MALAY vowel classification using multinomial logistic regression. COMPUSOFT: An International Journal of Advanced Computer Technology, 7(11), 2862–2866. Retrieved from https://ijact.in/index.php/j/article/view/451

Issue

Section

Original Research Article

Similar Articles

<< < 3 4 5 6 7 8 9 10 > >> 

You may also start an advanced similarity search for this article.