Building a system to identify individuals through their speech recording can find its application in diverse areas, such as telephone shopping, voice mail and security control. However, building such systems is a tricky task because of the vast range of differences in the human voice. Thus, selecting strong features becomes very crucial for the recognition system. Therefore, a speaker recognition system based on new spin-image descriptors (SISR) is proposed in this paper. In the proposed system, circular windows (spins) are extracted from the frequency domain of the spectrogram image of the sound, and then a run length matrix is built for each spin, to work as a base for feature extraction tasks. Five different descriptors are generated fro

Deep learning convolution neural network has been widely used to recognize or classify voice. Various techniques have been used together with convolution neural network to prepare voice data before the training process in developing the classification model. However, not all model can produce good classification accuracy as there are many types of voice or speech. Classification of Arabic alphabet pronunciation is a one of the types of voice and accurate pronunciation is required in the learning of the Qur’an reading. Thus, the technique to process the pronunciation and training of the processed data requires specific approach. To overcome this issue, a method based on padding and deep learning convolution neural network is proposed to

This paper proposes a novel method for generating True Random Numbers (TRNs) using electromechanical switches. The proposed generator is implemented using an FPGA board. The system utilizes the phenomenon of electromechanical switch bounce to produce a randomly fluctuated signal that is used to trigger a counter to generate a binary random number. Compared to other true random number generation methods, the proposed approach features a high degree of randomness using a simple circuit that can be easily built using off-the-shelf components. The proposed system is implemented using a commercial relay circuit connected to an FPGA board that is used to process and record the generated random sequences. Applying statistical testing on th

This paper proposes a novel method for generating True Random Numbers (TRNs) using electromechanical switches. The proposed generator is implemented using an FPGA board. The system utilizes the phenomenon of electromechanical switch bounce to produce a randomly fluctuated signal that is used to trigger a counter to generate a binary random number. Compared to other true random number generation methods, the proposed approach features a high degree of randomness using a simple circuit that can be easily built using off-the-shelf components. The proposed system is implemented using a commercial relay circuit connected to an FPGA board that is used to process and record the generated random sequences. Applying statistical testing on the exp

Compressing the speech reduces the data storage requirements, leading to reducing the time of transmitting the digitized speech over long-haul links like internet. To obtain best performance in speech compression, wavelet transforms require filters that combine a number of desirable properties, such as orthogonality and symmetry.The MCT bases functions are derived from GHM bases function using 2D linear convolution .The fast computation algorithm methods introduced here added desirable features to the current transform. We further assess the performance of the MCT in speech compression application. This paper discusses the effect of using DWT and MCT (one and two dimension) on speech compression. DWT and MCT performances in terms of comp

            Human Interactive Proofs (HIPs) are automatic inverse Turing tests, which are intended to differentiate between people and malicious computer programs. The mission of making good HIP system is a challenging issue, since the resultant HIP must be secure against attacks and in the same time it must be practical for humans. Text-based HIPs is one of the most popular HIPs types. It exploits the capability of humans to recite text images more than Optical Character Recognition (OCR), but the current text-based HIPs are not well-matched with rapid development of computer vision techniques, since they are either vey simply passed or very hard to resolve, thus this motivate that

This study aims to reveal the similarities and differences between Iraqi and Malay university learners and their genders in producing the supportive moves of criticism. To this end, 30 Iraqi and 30 Malay university learners have participated in this study. A Discourse Completion Test (DCT) and a Focus Group Interview (FGI) are conducted to elicit responses from the participants. Nguyen’s (2005) classification of criticism supportive moves is adapted to code the data. The data are analysed qualitatively and quantitatively. Overall, the findings unveil that both groups use similar categories of supportive moves, but Iraqis produce more of these devices than Malays in their criticisms. Although both females and males of both groups use id