Wavelet LPC with Neural Network for Spoken Arabic Digits Recognition System
K. Daqrouq *
Electrical and Computer Engineering Department, King Abdulaziz University, Saudi Arabia.
M. Alfaouri
Department of Electrical and Communications, Al-balqa Applied University Faculty of Engineering and Technology, Jordan.
A. Alkhateeb
Electrical and Computer Engineering Department, King Abdulaziz University, Saudi Arabia.
E. Khalaf
Electrical and Computer Engineering Department, King Abdulaziz University, Saudi Arabia.
A. Morfeq
Electrical and Computer Engineering Department, King Abdulaziz University, Saudi Arabia.
*Author to whom correspondence should be addressed.
Abstract
The crucial problem of Arabic recognition systems is the availability of several dialects in Arabic language, particularly those with sound variations. Therefore, low recognition rate is encountered as a result of such an environment. In this research paper the authors presented dialect-independent via an enormously effectual wavelet transform (WT) based Arabic digits classier. The proposed system may be divided into two main blocks the features extraction method by combining wavelet transform with the linear prediction coding (LPC) and the classiï¬cation by probabilistic neural network (PNN). The proposed classier provided a high recognition rate reaching up to 100%, in some cases, and an average rate of about 93% based on speaker-independent system. 450 Arabic spoken digit tested signals were used. The performance of the system in the noisy environment was investigated. The obtained results are very promising; however, the larger testing database may provide more credible results.
Keywords: Arabic digits, wavelet transform, speech recognition, LPC, neural network