Arabic isolated word recognition system using hybrid feature extraction techniques and neural network
- 148 Downloads
In this paper, we implemented a speaker-dependent speech recognition system for 11 standard Arabic isolated words. During the feature extraction phase, several techniques were used such as Mel frequency cepstral coefficients, perceptual linear prediction, relative perceptual linear prediction and their first order temporal derivatives. Principal component analysis was adopted in order to reduce the feature dimension. The recognition phase is based on the feed forward back-propagation neural network using two learning algorithms: the Levenberg–Marquardt “Trainlm” and the scaled conjugate gradient “Trainscg”. Hybrid approaches were used and compared in terms of computational time and recognition rates and have produced very interesting performances.
KeywordsSpeech recognition Mel frequency cepstral coefficients Perceptual linear predictive Principal component analysis Feed forward back-propagation neural network
The funding was supported by LARATSI Lab.
- Al-Irhayim, Y. F., & Hussein, M. K. (2016). Speech recognition of isolated Arabic words via using wavelet transformation and fuzzy neural network. In Computer engineering and intelligent systems (Vol. 7, No.3).Google Scholar
- El Kourd, A. (2014). Arabic isolated word speaker dependent recognition system, Thesis, Islamic University, Gaza, Palestine, Faculty of Engineering, Computer Engineering Department.Google Scholar
- El Kourd, A., & El Kourd, K. (2016). Arabic isolated word speaker dependent recognition system. British Journal of Mathematics & Computer Science 1–15.Google Scholar
- Elouahabi, S., Atounti, M., Bellouki, M. (2016). Amazigh Isolated Word Speech Recognition System Using Hidden Markov Model Toolkit (HTK). In IEEE Xplore, International Conference on Information Technology for Organizations Development (IT4OD) (pp. 1–7). https://doi.org/10.1109/IT4OD.2016.7479305.
- Hamdan, S., & Shaout, A. (2016). Hybrid Arabic speech recognition system using FFT, fuzzy logic and neural network, IRACST: International Journal of Computer Science and Information Technology & Security (IJCSITS), 6(No.4).Google Scholar
- Hassine, M., Boussaid, L., & Massaoud, H. (2016). Maghrebian dialect recognition based on support vector machines and neural network classifiers. International Journal of Speech Technology 19(4), 687–695.Google Scholar
- Haykin, S. (2009). Neural networks and learning machines. New York: Prentice Hall.Google Scholar
- Murphy, A. (2014). Implementing speech recognition with artificial neural networks. Ontario: Algoma University Sault Ste. Marie.Google Scholar
- Perera, K. A. D., Ranathunga, R. A. D. S., Welivyitigoda, I. P., & Withanawasaw, R. M. (2005). Isolated word recognition. In International Conference on Information and Automation, December15–18, Colombo, Sri Lanka.Google Scholar
- Qasim, M., Nawaz, S., Hussain, S., & Habib, T., (2016) Urdu speech recognition system for district names of Pakistan: Development, challenges and solutions. In Conference of the Oriental Chapter of International Committee for Coordination and Standardization of Speech Databases and Assessment Technique (O-COCOSDA), (pp. 26–28). Bali, Indonesia.Google Scholar
- Saksamudre, S. K. (2015). Comparative study of isolated word recognition system for Hindi language. IJERT, 4(7), 536–540.Google Scholar
- Shlens, J. (2003). A tutorial on principal component analysis derivation, discussion and singular value decomposition, UCSD. Retrieved from https://pdfs.semanticscholar.org/d3cd/d4aa72f0e4e0952c67cf911d1d1e4ff8e796.pdf.
- Sukminder, S. G., & Dinesh, K. (2010). Isolated word recognition system for English language. International Journal of Information Technology and Knowledge Management, July-December, 2(2), 447–450.Google Scholar
- Venkateswarlu, R. L. K., Kumari, R. V., & Vani Jayasri, G. (2011) Speech recognition using radial basis function neural network. In Proceedings of the 3rd International Conference on Electronics Computer Technology, April 8–10, (pp. 441–445). IEEE Xplore, Kanyakumari, 5941788. https://doi.org/10.1109/ICECTECH.