Abstract—In this work, an enhancement of a previously published work that tackles the use of automatic speaker verification (ASV) techniques in the Beyond Third generation (B3G) cellular systems has been proposed. The new proposition has been studied to overcome the effect of the Peak-to-Average Power Ratio (PAPR), which is a vital problem that found in the Orthogonal Frequency Division Multiplexing (OFDM) techniques, where a powerful combination between two main technologies; Multiple-Input Multiple-Output (MIMO) and OFDM has been developed to meet the rapidly increment in the users demand such as the ubiquitous transmission, imposing new multimedia applications and wireless services. The work space has been divided into three main areas; firstly, reducing the ASV complexity by selecting the weight of the text independent speakers based on Self-Organizing Map (WSOM) Neural Network (NNT), secondly, using the Eigen values/vector extracting features techniques as a pre-processing one to enhance the orthogonality, and finally proposing a new algorithm to combat the effect of the PAPR in the MIMO-OFDM systems. In this algorithm, wavelets techniques have been used to Denoise the affected OFDM symbol by high PAPR values. After that and based on adaptive threshold method the local maxima and minima will be determined and replaced by the average of them and their surrounding neighbors; Denoise OFDM and Replace PAPR (DORP). A system performance investigation process will be accomplished based on both of numerical method and MATLAB simulation. Moreover, a comparison has been made to check the validity of our proposition with our previously published work. Although, the achieved results show that the proposed work has lower PAPR values; an additional complexity has been added to transceiver’s structure. Moreover, and as a result to the comparison with the conventional systems, the bit error rate (BER) performance has been improved for the same bandwidth occupancy. Our simulation results showed that around 28% extra reduction in PAPR over current values in the literature, it can be achieved depending on the system type. Moreover, two different investigation and verifications techniques have been used in this work; Gaussian mixture model based method (GMMWPE) and K-Means clustering based method (KMWPE). A O. R. Daoud is in Department of Communication and Electronics, Philadelphia University, Jordan., (corresponding author: 962785583769; fax:96264799037; e-mail: odaoud@philadelphia.edu.jo ). Q. J. Hamarsheh is in Department of Computer Engineering, Philadelphia University, Jordan. W. H. AlSawalmeh is with Department of Communication Engineering, Al-Hussein Bin Talal University, Ma’an, Jordan. promising verifications result has been showed for verifications rate; around 91% and for noise immunity. Keywords—MIMO, OFDM, Peak-to-Average Power Ratio, Self- Organizing map, Wavelet, Eigen vectors. I. INTRODUCTION ver the last decade and due to the overwhelming huge data that the users’ create, transmit and/or manage; a challenge has been made to the wireless communication systems vendors to ease such complexities This will produce advanced wireless techniques with high capacity and restrain the growth in the multimedia applications, internet access either wired or wireless and other needed applications in the new generation mobile systems. One of the main challenging issues is Speaker verification. It has been the topic of active research for many years, and has many important applications where propriety of information is a concern [1]. This is revealing that the speaker verification system is a difficult task. Typically, these intricacies contain the needed amount of speech for accurate verification and estimation; and the threshold estimation for acceptance and rejection [1-3]. Moreover, the unprecedented developments have been made to meet this rapidly increment in the users demand such as the ubiquitous transmission, imposing new multimedia applications and wireless services. An example of the technologies that have been developed to meet the increasing demand of reliability, coverage, the new services is the combination between two main techniques in cellular systems; Multiple-Input Multiple-Output -Orthogonal Frequency Division Multiplexing (MIMO-OFDM). This is to improve the system reliability and performance. For more improvement, a pre-processing technique has been introduced to increase the orthogonality among the tested data which is based on imposing the Eigen values/vector extracting features. Orthogonal frequency division multiplexing has emerged as an efficient multicarrier modulation scheme for wireless, frequency selective, communication channels. Ease of implementation, high spectral efficiency, resilience to impulse noise and multipath are a few advantages of OFDM systems. It is a multi-carrier system which utilizes a parallel processing technique allowing the simultaneous transmission of data on Speaker Verification over MIMO-OFDM Systems based on Artificial Intelligence Techniques Omar R. Daoud, Qadri J. Hamarsheh, and Wael H. Al-Sawalmeh O INTERNATIONAL JOURNAL OF COMPUTERS AND COMMUNICATIONS Issue 4, Volume 6, 2012 191