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 evaluate the pronunciation of the Arabic alphabet. Voice data from six school children are recorded and used to test the performance of the proposed method. The padding technique has been used to augment the voice data before feeding the data to the CNN structure to developed the classification model. In addition, three other feature extraction techniques have been introduced to enable the comparison of the proposed method which employs padding technique. The performance of the proposed method with padding technique is at par with the spectrogram but better than mel-spectrogram and mel-frequency cepstral coefficients. Results also show that the proposed method was able to distinguish the Arabic alphabets that are difficult to pronounce. The proposed method with padding technique may be extended to address other voice pronunciation ability other than the Arabic alphabets.
In this work the effect of choosing tri-circular tube section had been addressed to minimize the end effector’s error, a comparison had been made between the tri-tube section and the traditional square cross section for a robot arm, the study shows that for the same weight of square section and tri-tube section the error may be reduced by about 33%.
A program had been built up by the use of MathCAD software to calculate the minimum weight of a square section robot arm that could with stand a given pay load and gives a minimum deflection. The second part of the program makes an optimization process for the dimension of the cross section and gives the dimensions of the tri-circular tube cross section that have the same weight of
... Show MoreThe present study stresses two of the most significant aspects of linguistic approach: Pragmatics” and the “Speech Act Theory”, revealing its importance and the stages and levels of development through Hebrew language’s speech acts analysis including (political speech, the Holy Bible, Hebrew stories).
Chronologically, Pragmatics has always been the center of linguists’ interests due to its importance in linguistic decryptions, particularly, through “Speech Act Theory” that has been initiated and developed by the most prominent philosophers and linguistics.
The prese
... Show MoreThis search has introduced the techniques of multi-wavelet transform and neural network for recognition 3-D object from 2-D image using patches. The proposed techniques were tested on database of different patches features and the high energy subband of discrete multi-wavelet transform DMWT (gp) of the patches. The test set has two groups, group (1) which contains images, their (gp) patches and patches features of the same images as a part of that in the data set beside other images, (gp) patches and features, and group (2) which contains the (gp) patches and patches features the same as a part of that in the database but after modification such as rotation, scaling and translation. Recognition by back propagation (BP) neural network as com
... Show MoreThis search has introduced the techniques of multi-wavelet transform and neural network for recognition 3-D object from 2-D image using patches. The proposed techniques were tested on database of different patches features and the high energy subband of discrete multi-wavelet transform DMWT (gp) of the patches. The test set has two groups, group (1) which contains images, their (gp) patches and patches features of the same images as a part of that in the data set beside other images, (gp) patches and features, and group (2) which contains the (gp) patches and patches features the same as a part of that in the database but after modification such as rotation, scaling and translation. Recognition by back propagation (BP) neural network as
... Show MoreThis work implements an Electroencephalogram (EEG) signal classifier. The implemented method uses Orthogonal Polynomials (OP) to convert the EEG signal samples to moments. A Sparse Filter (SF) reduces the number of converted moments to increase the classification accuracy. A Support Vector Machine (SVM) is used to classify the reduced moments between two classes. The proposed method’s performance is tested and compared with two methods by using two datasets. The datasets are divided into 80% for training and 20% for testing, with 5 -fold used for cross-validation. The results show that this method overcomes the accuracy of other methods. The proposed method’s best accuracy is 95.6% and 99.5%, respectively. Finally, from the results, it
... Show MoreData scarcity is a major challenge when training deep learning (DL) models. DL demands a large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate data to train DL frameworks. Usually, manual labeling is needed to provide labeled data, which typically involves human annotators with a vast background of knowledge. This annotation process is costly, time-consuming, and error-prone. Usually, every DL framework is fed by a significant amount of labeled data to automatically learn representations. Ultimately, a larger amount of data would generate a better DL model and its performance is also application dependent. This issue is the main barrier for