Kurdish Spoken Letter Recognition based on k-NN and SVM Model

  • Zrar Khalid Abdul Department of ApplyingComputer , College of Medicals and Applied Science ,Charmo University, Chamchamal, Kurdistan Region, Iraq.
Keywords: K-Nearest Neighbor, Support Vector Machine, Confusion Matrix, LPC, MFCC.

Abstract

Automatic recognition of spoken letters is one of the most challenging tasks in the area of speech recognition system. In this paper, different machine learning approaches are used to classify the Kurdish alphabets such as SVM and k-NN where both approaches are fed by two different features, Linear Predictive Coding (LPC) and Mel Frequency Cepstral Coefficients (MFCCs). Moreover, the features are combined together to learn the classifiers. The experiments are evaluated on the dataset that are collected by the authors as there as not standard Kurdish dataset. The dataset consists of 2720 samples as a total. The results show that the MFCC features outperforms the LPC features as the MFCCs have more relative information of vocal track. Furthermore, fusion of the features (MFCC and LPC) is not capable to improve the classification rate significantly.

References

Abdul, Z.K., 2019. Kurdish speaker identification based on one dimensional convolutional neural network-Computational Methods for Differential Equations, , University of Tabriz,7, 566–572.
Al-Talabani, A., Abdul, Z., Ameen, A., 2017. Kurdish Dialects and Neighbor Languages Automatic Recognition. ARO-The Sci. J. Koya Univ. 5, 20–23.
Alotaibi, Y.A., Alghamdi, M., Alotaiby, F., 2010. Speech recognition system of Arabic alphabet based on a telephony Arabic corpus. Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics) 6134 LNCS, 122–129.
Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., Casper, J., Catanzaro, B., Cheng, Q., Chen, G., others, 2016. Deep speech 2: End-to-end speech recognition in english and mandarin. In: International Conference on Machine Learning. pp. 173–182.
B.Adam, T., Salam, M., 2012. Spoken English Alphabet Recognition with Mel Frequency Cepstral Coefficients and Back Propagation Neural Networks. Int. J. Comput. Appl. 42, 21–27.
Bäckström, T., 2017. Speech Coding: with Code-Excited Linear Prediction. Springer.
Cited, R., Hamdani, M., 2018. Discrete hidden markov model basis for arabic handwriting recognition 1.
Cole, R.A., Muthusamy, Y., Tutor, M.S., 1990. Speaker-independent recognition of spoken English letters Speaker-Independent Recognition of Spoken English Letters.
Dhameliya, K., Bhatt, N., 2015. Feature extraction and classification techniques for speaker recognition: A review. Int. Conf. Electr. Electron. Signals, Commun. Optim. EESCO 2015 3, 1–5.
Dinler, O.B., Karabiber, F., 2017. Formant analysis of vowels in Kurdish language. In: 2017 25th Signal Processing and Communications Applications Conference (SIU). IEEE, pp. 1–4.
Fernandes, V., Mascarehnas, L., Mendonca, C., Johnson, A., Mishra, R., 2018. Speech Emotion Recognition using Mel Frequency Cepstral Coefficient and SVM Classifier. In: 2018 International Conference on System Modeling & Advancement in Research Trends (SMART). pp. 200–204.
Hibare, R., Vibhute, A., 2014. Feature Extraction Techniques in Speech Processing: A Survey. Int. J. Comput. Appl. 107, 1–8.
Jadhav, S.D., Channe, H.P., 2016. Comparative Study of K-NN, Naive Bayes and Decision Tree Classification Techniques. Int. J. Sci. Res. 5, 1842–1845.
Jan, P., 1943. ‘ UNITED .sTAT-Es PATENT - 12, 2–4.
McCarus, E.N., 2013. Kurdish. In: The Iranian Languages. Routledge, pp. 663–709.
Meyer, B.T., Brand, T., Kollmeier, B., 2011. Effect of speech-intrinsic variations on human and automatic recognition of spoken phonemes. J. Acoust. Soc. Am. 129, 388–403.
Nayak, J., Naik, B., Behera, H.S., 2015. A Comprehensive Survey on Support Vector Machine in Data Mining Tasks: Applications & Challenges. Int. J. Database Theory Appl. 8, 169–186.
Omer, S.M., 2019. Uttered Kurdish digit recognition system 6, 78–85.
Saon, G., Kurata, G., Sercu, T., Audhkhasi, K., Thomas, S., Dimitriadis, D., Cui, X., Ramabhadran, B., Picheny, M., Lim, L.-L., others, 2017. English conversational telephone speech recognition by humans and machines. arXiv Prepr. arXiv1703.02136.
SAYEM, A., 2014. Speech Analysis for Alphabets in Bangla Language: Automatic Speech Recognition. Int. J. Eng. Res. 3, 88–93.
Sheyholislami, J., 2011. Kurdish Identity. In: Kurdish Identity, Discourse, and New Media. Springer, pp. 47–77.
Vlontzos, J.A., Kung, S.-Y., 1989. Hidden Markov models for character recognition. In: International Conference on Acoustics, Speech, and Signal Processing,. pp. 1719–1722.
Published
2020-11-30
How to Cite
Abdul, Z. (2020). Kurdish Spoken Letter Recognition based on k-NN and SVM Model. Journal of University of Raparin, 7(4), 1-12. https://doi.org/10.26750/Vol(7).No(4).paper1